BibTeX records: Siddhant Arora

download as .bib file

@article{DBLP:journals/tmm/KimJRMACWR26,
  author       = {Minsu Kim and
                  Jee{-}Weon Jung and
                  Hyeongseop Rha and
                  Soumi Maiti and
                  Siddhant Arora and
                  Xuankai Chang and
                  Shinji Watanabe and
                  Yong Man Ro},
  title        = {{TMT:} Tri-Modal Translation Between Speech, Image, and Text by Processing
                  Different Modalities as Different Languages},
  journal      = {{IEEE} Trans. Multim.},
  volume       = {28},
  pages        = {1976--1988},
  year         = {2026},
  url          = {https://doi.org/10.1109/TMM.2026.3659297},
  doi          = {10.1109/TMM.2026.3659297},
  timestamp    = {Wed, 25 Mar 2026 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/tmm/KimJRMACWR26.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2601-02391,
  author       = {Zhaojiang Lin and
                  Yong Xu and
                  Kai Sun and
                  Jing Zheng and
                  Yin Huang and
                  Surya Teja Appini and
                  Krish Narang and
                  Renjie Tao and
                  Ishan Kapil Jain and
                  Siddhant Arora and
                  Ruizhi Li and
                  Yiteng Huang and
                  Kaushik Patnaik and
                  Wenfang Xu and
                  Suwon Shon and
                  Yue Liu and
                  Ahmed Aly and
                  Anuj Kumar and
                  Florian Metze and
                  Xin Luna Dong},
  title        = {WearVox: An Egocentric Multichannel Voice Assistant Benchmark for
                  Wearables},
  journal      = {CoRR},
  volume       = {abs/2601.02391},
  year         = {2026},
  url          = {https://doi.org/10.48550/arXiv.2601.02391},
  doi          = {10.48550/ARXIV.2601.02391},
  eprinttype   = {arXiv},
  eprint       = {2601.02391},
  timestamp    = {Wed, 11 Feb 2026 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2601-02391.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2601-19063,
  author       = {Siddhant Arora and
                  Jinchuan Tian and
                  Jiatong Shi and
                  Hayato Futami and
                  Yosuke Kashiwagi and
                  Emiru Tsunoo and
                  Shinji Watanabe},
  title        = {Optimizing Conversational Quality in Spoken Dialogue Systems with
                  Reinforcement Learning from {AI} Feedback},
  journal      = {CoRR},
  volume       = {abs/2601.19063},
  year         = {2026},
  url          = {https://doi.org/10.48550/arXiv.2601.19063},
  doi          = {10.48550/ARXIV.2601.19063},
  eprinttype   = {arXiv},
  eprint       = {2601.19063},
  timestamp    = {Thu, 26 Feb 2026 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2601-19063.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2602-05220,
  author       = {Jinchuan Tian and
                  Haoran Wang and
                  Bo{-}Hao Su and
                  Chien{-}Yu Huang and
                  Qingzheng Wang and
                  Jiatong Shi and
                  William Chen and
                  Xun Gong and
                  Siddhant Arora and
                  Chin{-}Jou Li and
                  Masao Someki and
                  Takashi Maekaku and
                  Keita Goto and
                  Yusuke Shinohara and
                  Jin Sakuma and
                  Chao{-}Han Huck Yang and
                  Shinji Watanabe},
  title        = {Bagpiper: Solving Open-Ended Audio Tasks via Rich Captions},
  journal      = {CoRR},
  volume       = {abs/2602.05220},
  year         = {2026},
  url          = {https://doi.org/10.48550/arXiv.2602.05220},
  doi          = {10.48550/ARXIV.2602.05220},
  eprinttype   = {arXiv},
  eprint       = {2602.05220},
  timestamp    = {Fri, 20 Mar 2026 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2602-05220.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/dai/AroraBK25,
  author       = {Siddhant Arora and
                  Ahaan Banerjee and
                  Nitish Katal},
  title        = {Enhanced urban driving scene segmentation using modified UNet with
                  residual convolutions and attention guided skip connections},
  journal      = {Discov. Artif. Intell.},
  volume       = {5},
  number       = {1},
  pages        = {198},
  year         = {2025},
  url          = {https://doi.org/10.1007/s44163-025-00455-x},
  doi          = {10.1007/S44163-025-00455-X},
  timestamp    = {Wed, 25 Feb 2026 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/dai/AroraBK25.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tmlr/AroraCCPWADLLW25,
  author       = {Siddhant Arora and
                  Kai{-}Wei Chang and
                  Chung{-}Ming Chien and
                  Yifan Peng and
                  Haibin Wu and
                  Yossi Adi and
                  Emmanuel Dupoux and
                  Hung{-}yi Lee and
                  Karen Livescu and
                  Shinji Watanabe},
  title        = {On The Landscape of Spoken Language Models: {A} Comprehensive Survey},
  journal      = {Trans. Mach. Learn. Res.},
  volume       = {2025},
  year         = {2025},
  url          = {https://openreview.net/forum?id=BvxaP3sVbA},
  timestamp    = {Sun, 08 Feb 2026 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/tmlr/AroraCCPWADLLW25.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KashiwagiFTA025,
  author       = {Yosuke Kashiwagi and
                  Hayato Futami and
                  Emiru Tsunoo and
                  Siddhant Arora and
                  Shinji Watanabe},
  title        = {Hypothesis Clustering and Merging: Novel MultiTalker Speech Recognition
                  with Speaker Tokens},
  booktitle    = {2025 {IEEE} International Conference on Acoustics, Speech and Signal
                  Processing, {ICASSP} 2025, Hyderabad, India, April 6-11, 2025},
  pages        = {1--5},
  publisher    = {{IEEE}},
  year         = {2025},
  url          = {https://doi.org/10.1109/ICASSP49660.2025.10888002},
  doi          = {10.1109/ICASSP49660.2025.10888002},
  timestamp    = {Thu, 25 Dec 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/icassp/KashiwagiFTA025.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/AroraLCP025,
  author       = {Siddhant Arora and
                  Zhiyun Lu and
                  Chung{-}Cheng Chiu and
                  Ruoming Pang and
                  Shinji Watanabe},
  title        = {Talking Turns: Benchmarking Audio Foundation Models on Turn-Taking
                  Dynamics},
  booktitle    = {The Thirteenth International Conference on Learning Representations,
                  {ICLR} 2025, Singapore, April 24-28, 2025},
  publisher    = {OpenReview.net},
  year         = {2025},
  url          = {https://openreview.net/forum?id=2e4ECh0ikn},
  timestamp    = {Thu, 15 May 2025 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/iclr/AroraLCP025.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/SomekiPAMMSL025,
  author       = {Masao Someki and
                  Yifan Peng and
                  Siddhant Arora and
                  Markus M{\"{u}}ller and
                  Athanasios Mouchtaris and
                  Grant P. Strimel and
                  Jing Liu and
                  Shinji Watanabe},
  title        = {Context-aware Dynamic Pruning for Speech Foundation Models},
  booktitle    = {The Thirteenth International Conference on Learning Representations,
                  {ICLR} 2025, Singapore, April 24-28, 2025},
  publisher    = {OpenReview.net},
  year         = {2025},
  url          = {https://openreview.net/forum?id=u2QdCiOgwA},
  timestamp    = {Mon, 30 Jun 2025 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/iclr/SomekiPAMMSL025.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/AroraTFJSKT025,
  author       = {Siddhant Arora and
                  Jinchuan Tian and
                  Hayato Futami and
                  Jee{-}weon Jung and
                  Jiatong Shi and
                  Yosuke Kashiwagi and
                  Emiru Tsunoo and
                  Shinji Watanabe},
  editor       = {Odette Scharenborg and
                  Catharine Oertel and
                  Khiet Truong},
  title        = {Chain-of-Thought Training for Open {E2E} Spoken Dialogue Systems},
  booktitle    = {26th Annual Conference of the International Speech Communication Association,
                  Interspeech 2025, Rotterdam, The Netherlands, 17-21 August 2025},
  publisher    = {{ISCA}},
  year         = {2025},
  url          = {https://doi.org/10.21437/Interspeech.2025-2339},
  doi          = {10.21437/INTERSPEECH.2025-2339},
  timestamp    = {Thu, 20 Nov 2025 11:03:39 +0100},
  biburl       = {https://dblp.org/rec/conf/interspeech/AroraTFJSKT025.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/FutamiTKISA025,
  author       = {Hayato Futami and
                  Emiru Tsunoo and
                  Yosuke Kashiwagi and
                  Yuki Ito and
                  Hassan Shahmohammadi and
                  Siddhant Arora and
                  Shinji Watanabe},
  editor       = {Odette Scharenborg and
                  Catharine Oertel and
                  Khiet Truong},
  title        = {Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation
                  with LLMs},
  booktitle    = {26th Annual Conference of the International Speech Communication Association,
                  Interspeech 2025, Rotterdam, The Netherlands, 17-21 August 2025},
  publisher    = {{ISCA}},
  year         = {2025},
  url          = {https://doi.org/10.21437/Interspeech.2025-1595},
  doi          = {10.21437/INTERSPEECH.2025-1595},
  timestamp    = {Thu, 20 Nov 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/interspeech/FutamiTKISA025.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SheikhSASCL025,
  author       = {Zaid Sheikh and
                  Shuichiro Shimizu and
                  Siddhant Arora and
                  Jiatong Shi and
                  Samuele Cornell and
                  Xinjian Li and
                  Shinji Watanabe},
  editor       = {Odette Scharenborg and
                  Catharine Oertel and
                  Khiet Truong},
  title        = {Scalable Spontaneous Speech Dataset {(SSSD):} Crowdsourcing Data Collection
                  to Promote Dialogue Research},
  booktitle    = {26th Annual Conference of the International Speech Communication Association,
                  Interspeech 2025, Rotterdam, The Netherlands, 17-21 August 2025},
  publisher    = {{ISCA}},
  year         = {2025},
  url          = {https://doi.org/10.21437/Interspeech.2025-2362},
  doi          = {10.21437/INTERSPEECH.2025-2362},
  timestamp    = {Thu, 20 Nov 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/interspeech/SheikhSASCL025.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/TianC0SABMSGYY025,
  author       = {Jinchuan Tian and
                  William Chen and
                  Yifan Peng and
                  Jiatong Shi and
                  Siddhant Arora and
                  Shikhar Bharadwaj and
                  Takashi Maekaku and
                  Yusuke Shinohara and
                  Keita Goto and
                  Xiang Yue and
                  Huck Yang and
                  Shinji Watanabe},
  editor       = {Odette Scharenborg and
                  Catharine Oertel and
                  Khiet Truong},
  title        = {OpusLM: {A} Family of Open Unified Speech Language Models},
  booktitle    = {26th Annual Conference of the International Speech Communication Association,
                  Interspeech 2025, Rotterdam, The Netherlands, 17-21 August 2025},
  publisher    = {{ISCA}},
  year         = {2025},
  url          = {https://doi.org/10.21437/Interspeech.2025-1184},
  doi          = {10.21437/INTERSPEECH.2025-1184},
  timestamp    = {Thu, 25 Dec 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/interspeech/TianC0SABMSGYY025.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/naacl/TianSCAMMWPBZC025,
  author       = {Jinchuan Tian and
                  Jiatong Shi and
                  William Chen and
                  Siddhant Arora and
                  Yoshiki Masuyama and
                  Takashi Maekaku and
                  Yihan Wu and
                  Junyi Peng and
                  Shikhar Bharadwaj and
                  Yiwen Zhao and
                  Samuele Cornell and
                  Yifan Peng and
                  Xiang Yue and
                  Chao{-}Han Huck Yang and
                  Graham Neubig and
                  Shinji Watanabe},
  editor       = {Nouha Dziri and
                  Sean (Xiang) Ren and
                  Shizhe Diao},
  title        = {ESPnet-SpeechLM: An Open Speech Language Model Toolkit},
  booktitle    = {Proceedings of the 2025 Conference of the Nations of the Americas
                  Chapter of the Association for Computational Linguistics: Human Language
                  Technologies, {NAACL} 2025 - System Demonstrations, Albuquerque, New
                  Mexico, USA, April 29 - May 4, 2025},
  pages        = {116--124},
  publisher    = {Association for Computational Linguistics},
  year         = {2025},
  url          = {https://doi.org/10.18653/v1/2025.naacl-demo.12},
  doi          = {10.18653/V1/2025.NAACL-DEMO.12},
  timestamp    = {Wed, 25 Feb 2026 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/naacl/TianSCAMMWPBZC025.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/naacl/ShiSTAWPYZTZAHS25,
  author       = {Jiatong Shi and
                  Hye{-}jin Shim and
                  Jinchuan Tian and
                  Siddhant Arora and
                  Haibin Wu and
                  Darius Petermann and
                  Jia Qi Yip and
                  You Zhang and
                  Yuxun Tang and
                  Wangyou Zhang and
                  Dareen Alharthi and
                  Yichen Huang and
                  Koichi Saito and
                  Jionghao Han and
                  Yiwen Zhao and
                  Chris Donahue and
                  Shinji Watanabe},
  editor       = {Nouha Dziri and
                  Sean (Xiang) Ren and
                  Shizhe Diao},
  title        = {{VERSA:} {A} Versatile Evaluation Toolkit for Speech, Audio, and Music},
  booktitle    = {Proceedings of the 2025 Conference of the Nations of the Americas
                  Chapter of the Association for Computational Linguistics: Human Language
                  Technologies, {NAACL} 2025 - System Demonstrations, Albuquerque, New
                  Mexico, USA, April 29 - May 4, 2025},
  pages        = {191--209},
  publisher    = {Association for Computational Linguistics},
  year         = {2025},
  url          = {https://doi.org/10.18653/v1/2025.naacl-demo.19},
  doi          = {10.18653/V1/2025.NAACL-DEMO.19},
  timestamp    = {Tue, 03 Feb 2026 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/naacl/ShiSTAWPYZTZAHS25.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/naacl/Arora0STCBFKTSS25,
  author       = {Siddhant Arora and
                  Yifan Peng and
                  Jiatong Shi and
                  Jinchuan Tian and
                  William Chen and
                  Shikhar Bharadwaj and
                  Hayato Futami and
                  Yosuke Kashiwagi and
                  Emiru Tsunoo and
                  Shuichiro Shimizu and
                  Vaibhav Srivastav and
                  Shinji Watanabe},
  editor       = {Nouha Dziri and
                  Sean (Xiang) Ren and
                  Shizhe Diao},
  title        = {ESPnet-SDS: Unified Toolkit and Demo for Spoken Dialogue Systems},
  booktitle    = {Proceedings of the 2025 Conference of the Nations of the Americas
                  Chapter of the Association for Computational Linguistics: Human Language
                  Technologies, {NAACL} 2025 - System Demonstrations, Albuquerque, New
                  Mexico, USA, April 29 - May 4, 2025},
  pages        = {248--259},
  publisher    = {Association for Computational Linguistics},
  year         = {2025},
  url          = {https://doi.org/10.18653/v1/2025.naacl-demo.21},
  doi          = {10.18653/V1/2025.NAACL-DEMO.21},
  timestamp    = {Tue, 03 Feb 2026 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/naacl/Arora0STCBFKTSS25.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2502-15218,
  author       = {Jinchuan Tian and
                  Jiatong Shi and
                  William Chen and
                  Siddhant Arora and
                  Yoshiki Masuyama and
                  Takashi Maekaku and
                  Yihan Wu and
                  Junyi Peng and
                  Shikhar Bharadwaj and
                  Yiwen Zhao and
                  Samuele Cornell and
                  Yifan Peng and
                  Xiang Yue and
                  Chao{-}Han Huck Yang and
                  Graham Neubig and
                  Shinji Watanabe},
  title        = {ESPnet-SpeechLM: An Open Speech Language Model Toolkit},
  journal      = {CoRR},
  volume       = {abs/2502.15218},
  year         = {2025},
  url          = {https://doi.org/10.48550/arXiv.2502.15218},
  doi          = {10.48550/ARXIV.2502.15218},
  eprinttype   = {arXiv},
  eprint       = {2502.15218},
  timestamp    = {Sat, 07 Feb 2026 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2502-15218.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2503-01174,
  author       = {Siddhant Arora and
                  Zhiyun Lu and
                  Chung{-}Cheng Chiu and
                  Ruoming Pang and
                  Shinji Watanabe},
  title        = {Talking Turns: Benchmarking Audio Foundation Models on Turn-Taking
                  Dynamics},
  journal      = {CoRR},
  volume       = {abs/2503.01174},
  year         = {2025},
  url          = {https://doi.org/10.48550/arXiv.2503.01174},
  doi          = {10.48550/ARXIV.2503.01174},
  eprinttype   = {arXiv},
  eprint       = {2503.01174},
  timestamp    = {Thu, 25 Dec 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2503-01174.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2503-08533,
  author       = {Siddhant Arora and
                  Yifan Peng and
                  Jiatong Shi and
                  Jinchuan Tian and
                  William Chen and
                  Shikhar Bharadwaj and
                  Hayato Futami and
                  Yosuke Kashiwagi and
                  Emiru Tsunoo and
                  Shuichiro Shimizu and
                  Vaibhav Srivastav and
                  Shinji Watanabe},
  title        = {ESPnet-SDS: Unified Toolkit and Demo for Spoken Dialogue Systems},
  journal      = {CoRR},
  volume       = {abs/2503.08533},
  year         = {2025},
  url          = {https://doi.org/10.48550/arXiv.2503.08533},
  doi          = {10.48550/ARXIV.2503.08533},
  eprinttype   = {arXiv},
  eprint       = {2503.08533},
  timestamp    = {Thu, 25 Dec 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2503-08533.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2504-08528,
  author       = {Siddhant Arora and
                  Kai{-}Wei Chang and
                  Chung{-}Ming Chien and
                  Yifan Peng and
                  Haibin Wu and
                  Yossi Adi and
                  Emmanuel Dupoux and
                  Hung{-}Yi Lee and
                  Karen Livescu and
                  Shinji Watanabe},
  title        = {On The Landscape of Spoken Language Models: {A} Comprehensive Survey},
  journal      = {CoRR},
  volume       = {abs/2504.08528},
  year         = {2025},
  url          = {https://doi.org/10.48550/arXiv.2504.08528},
  doi          = {10.48550/ARXIV.2504.08528},
  eprinttype   = {arXiv},
  eprint       = {2504.08528},
  timestamp    = {Sun, 04 Jan 2026 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2504-08528.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2505-03054,
  author       = {Orevaoghene Ahia and
                  Martijn Bartelds and
                  Kabir Ahuja and
                  Hila Gonen and
                  Valentin Hofmann and
                  Siddhant Arora and
                  Shuyue Stella Li and
                  Vishal Puttagunta and
                  Mofetoluwa Adeyemi and
                  Charishma Buchireddy and
                  Ben Walls and
                  Noah Bennett and
                  Shinji Watanabe and
                  Noah A. Smith and
                  Yulia Tsvetkov and
                  Sachin Kumar},
  title        = {{BLAB:} Brutally Long Audio Bench},
  journal      = {CoRR},
  volume       = {abs/2505.03054},
  year         = {2025},
  url          = {https://doi.org/10.48550/arXiv.2505.03054},
  doi          = {10.48550/ARXIV.2505.03054},
  eprinttype   = {arXiv},
  eprint       = {2505.03054},
  timestamp    = {Thu, 25 Dec 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2505-03054.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2505-24518,
  author       = {Jiatong Shi and
                  Yifan Cheng and
                  Bo{-}Hao Su and
                  Hye{-}jin Shim and
                  Jinchuan Tian and
                  Samuele Cornell and
                  Yiwen Zhao and
                  Siddhant Arora and
                  Shinji Watanabe},
  title        = {{ARECHO:} Autoregressive Evaluation via Chain-Based Hypothesis Optimization
                  for Speech Multi-Metric Estimation},
  journal      = {CoRR},
  volume       = {abs/2505.24518},
  year         = {2025},
  url          = {https://doi.org/10.48550/arXiv.2505.24518},
  doi          = {10.48550/ARXIV.2505.24518},
  eprinttype   = {arXiv},
  eprint       = {2505.24518},
  timestamp    = {Thu, 25 Dec 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2505-24518.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2506-00722,
  author       = {Siddhant Arora and
                  Jinchuan Tian and
                  Hayato Futami and
                  Jee{-}weon Jung and
                  Jiatong Shi and
                  Yosuke Kashiwagi and
                  Emiru Tsunoo and
                  Shinji Watanabe},
  title        = {Chain-of-Thought Training for Open {E2E} Spoken Dialogue Systems},
  journal      = {CoRR},
  volume       = {abs/2506.00722},
  year         = {2025},
  url          = {https://doi.org/10.48550/arXiv.2506.00722},
  doi          = {10.48550/ARXIV.2506.00722},
  eprinttype   = {arXiv},
  eprint       = {2506.00722},
  timestamp    = {Thu, 25 Dec 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2506-00722.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2506-10299,
  author       = {Hayato Futami and
                  Emiru Tsunoo and
                  Yosuke Kashiwagi and
                  Yuki Ito and
                  Hassan Shahmohammadi and
                  Siddhant Arora and
                  Shinji Watanabe},
  title        = {Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation
                  with LLMs},
  journal      = {CoRR},
  volume       = {abs/2506.10299},
  year         = {2025},
  url          = {https://doi.org/10.48550/arXiv.2506.10299},
  doi          = {10.48550/ARXIV.2506.10299},
  eprinttype   = {arXiv},
  eprint       = {2506.10299},
  timestamp    = {Thu, 25 Dec 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2506-10299.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2506-17611,
  author       = {Jinchuan Tian and
                  William Chen and
                  Yifan Peng and
                  Jiatong Shi and
                  Siddhant Arora and
                  Shikhar Bharadwaj and
                  Takashi Maekaku and
                  Yusuke Shinohara and
                  Keita Goto and
                  Xiang Yue and
                  Huck Yang and
                  Shinji Watanabe},
  title        = {OpusLM: {A} Family of Open Unified Speech Language Models},
  journal      = {CoRR},
  volume       = {abs/2506.17611},
  year         = {2025},
  url          = {https://doi.org/10.48550/arXiv.2506.17611},
  doi          = {10.48550/ARXIV.2506.17611},
  eprinttype   = {arXiv},
  eprint       = {2506.17611},
  timestamp    = {Thu, 25 Dec 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2506-17611.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2506-23049,
  author       = {Leander Melroy Maben and
                  Gayathri Ganesh Lakshmy and
                  Srijith Radhakrishnan and
                  Siddhant Arora and
                  Shinji Watanabe},
  title        = {{AURA:} Agent for Understanding, Reasoning, and Automated Tool Use
                  in Voice-Driven Tasks},
  journal      = {CoRR},
  volume       = {abs/2506.23049},
  year         = {2025},
  url          = {https://doi.org/10.48550/arXiv.2506.23049},
  doi          = {10.48550/ARXIV.2506.23049},
  eprinttype   = {arXiv},
  eprint       = {2506.23049},
  timestamp    = {Thu, 25 Dec 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2506-23049.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2508-16576,
  author       = {Anyu Ying and
                  Natarajan Balaji Shankar and
                  Chyi{-}Jiunn Lin and
                  Mohan Shi and
                  Pu Wang and
                  Hye{-}jin Shim and
                  Siddhant Arora and
                  Hugo Van hamme and
                  Abeer Alwan and
                  Shinji Watanabe},
  title        = {Benchmarking Training Paradigms, Dataset Composition, and Model Scaling
                  for Child {ASR} in ESPnet},
  journal      = {CoRR},
  volume       = {abs/2508.16576},
  year         = {2025},
  url          = {https://doi.org/10.48550/arXiv.2508.16576},
  doi          = {10.48550/ARXIV.2508.16576},
  eprinttype   = {arXiv},
  eprint       = {2508.16576},
  timestamp    = {Thu, 25 Dec 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2508-16576.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2510-00982,
  author       = {Emiru Tsunoo and
                  Hayato Futami and
                  Yosuke Kashiwagi and
                  Siddhant Arora and
                  Shinji Watanabe},
  title        = {Spiralformer: Low Latency Encoder for Streaming Speech Recognition
                  with Circular Layer Skipping and Early Exiting},
  journal      = {CoRR},
  volume       = {abs/2510.00982},
  year         = {2025},
  url          = {https://doi.org/10.48550/arXiv.2510.00982},
  doi          = {10.48550/ARXIV.2510.00982},
  eprinttype   = {arXiv},
  eprint       = {2510.00982},
  timestamp    = {Mon, 17 Nov 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2510-00982.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2510-02044,
  author       = {Siddhant Arora and
                  Haidar Khan and
                  Kai Sun and
                  Xin Luna Dong and
                  Sajal Choudhary and
                  Seungwhan Moon and
                  Xinyuan Zhang and
                  Adithya Sagar and
                  Surya Teja Appini and
                  Kaushik Patnaik and
                  Sanat Sharma and
                  Shinji Watanabe and
                  Anuj Kumar and
                  Ahmed Aly and
                  Yue Liu and
                  Florian Metze and
                  Zhaojiang Lin},
  title        = {Stream {RAG:} Instant and Accurate Spoken Dialogue Systems with Streaming
                  Tool Usage},
  journal      = {CoRR},
  volume       = {abs/2510.02044},
  year         = {2025},
  url          = {https://doi.org/10.48550/arXiv.2510.02044},
  doi          = {10.48550/ARXIV.2510.02044},
  eprinttype   = {arXiv},
  eprint       = {2510.02044},
  timestamp    = {Mon, 10 Nov 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2510-02044.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2510-02066,
  author       = {Siddhant Arora and
                  Jinchuan Tian and
                  Hayato Futami and
                  Jiatong Shi and
                  Yosuke Kashiwagi and
                  Emiru Tsunoo and
                  Shinji Watanabe},
  title        = {Chain-of-Thought Reasoning in Streaming Full-Duplex End-to-End Spoken
                  Dialogue Systems},
  journal      = {CoRR},
  volume       = {abs/2510.02066},
  year         = {2025},
  url          = {https://doi.org/10.48550/arXiv.2510.02066},
  doi          = {10.48550/ARXIV.2510.02066},
  eprinttype   = {arXiv},
  eprint       = {2510.02066},
  timestamp    = {Sun, 09 Nov 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2510-02066.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/acl/AroraPCHSJDCSLL24,
  author       = {Siddhant Arora and
                  Ankita Pasad and
                  Chung{-}Ming Chien and
                  Jionghao Han and
                  Roshan S. Sharma and
                  Jee{-}weon Jung and
                  Hira Dhamyal and
                  William Chen and
                  Suwon Shon and
                  Hung{-}yi Lee and
                  Karen Livescu and
                  Shinji Watanabe},
  editor       = {Lun{-}Wei Ku and
                  Andre Martins and
                  Vivek Srikumar},
  title        = {On the Evaluation of Speech Foundation Models for Spoken Language
                  Understanding},
  booktitle    = {Findings of the Association for Computational Linguistics, {ACL} 2024,
                  Bangkok, Thailand and virtual meeting, August 11-16, 2024},
  series       = {Findings of {ACL}},
  pages        = {11923--11938},
  publisher    = {Association for Computational Linguistics},
  year         = {2024},
  url          = {https://doi.org/10.18653/v1/2024.findings-acl.709},
  doi          = {10.18653/V1/2024.FINDINGS-ACL.709},
  timestamp    = {Tue, 27 Jan 2026 20:26:47 +0100},
  biburl       = {https://dblp.org/rec/conf/acl/AroraPCHSJDCSLL24.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/coling/GuptaGBPOANSW24,
  author       = {Sonu Gupta and
                  Geetika Gopi and
                  Harish Balaji and
                  Ellen Poplavska and
                  Nora O'Toole and
                  Siddhant Arora and
                  Thomas B. Norton and
                  Norman M. Sadeh and
                  Shomir Wilson},
  editor       = {Nicoletta Calzolari and
                  Min{-}Yen Kan and
                  V{\'{e}}ronique Hoste and
                  Alessandro Lenci and
                  Sakriani Sakti and
                  Nianwen Xue},
  title        = {Creation and Analysis of an International Corpus of Privacy Laws},
  booktitle    = {Proceedings of the 2024 Joint International Conference on Computational
                  Linguistics, Language Resources and Evaluation, {LREC/COLING} 2024,
                  20-25 May, 2024, Torino, Italy},
  pages        = {4092--4105},
  publisher    = {{ELRA} and {ICCL}},
  year         = {2024},
  url          = {https://aclanthology.org/2024.lrec-main.365},
  timestamp    = {Thu, 23 May 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/coling/GuptaGBPOANSW24.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/FutamiTKOA024,
  author       = {Hayato Futami and
                  Emiru Tsunoo and
                  Yosuke Kashiwagi and
                  Hiroaki Ogawa and
                  Siddhant Arora and
                  Shinji Watanabe},
  title        = {Phoneme-Aware Encoding for Prefix-Tree-Based Contextual {ASR}},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
                  {ICASSP} 2024, Seoul, Republic of Korea, April 14-19, 2024},
  pages        = {10641--10645},
  publisher    = {{IEEE}},
  year         = {2024},
  url          = {https://doi.org/10.1109/ICASSP48485.2024.10447652},
  doi          = {10.1109/ICASSP48485.2024.10447652},
  timestamp    = {Thu, 25 Dec 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/icassp/FutamiTKOA024.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/AroraS0K24,
  author       = {Siddhant Arora and
                  George Saon and
                  Shinji Watanabe and
                  Brian Kingsbury},
  title        = {Semi-Autoregressive Streaming {ASR} with Label Context},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
                  {ICASSP} 2024, Seoul, Republic of Korea, April 14-19, 2024},
  pages        = {11681--11685},
  publisher    = {{IEEE}},
  year         = {2024},
  url          = {https://doi.org/10.1109/ICASSP48485.2024.10446807},
  doi          = {10.1109/ICASSP48485.2024.10446807},
  timestamp    = {Thu, 25 Dec 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/icassp/AroraS0K24.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HuangLWHKWACSPS24,
  author       = {Chien{-}Yu Huang and
                  Ke{-}Han Lu and
                  Shih{-}Heng Wang and
                  Chi{-}Yuan Hsiao and
                  Chun{-}Yi Kuan and
                  Haibin Wu and
                  Siddhant Arora and
                  Kai{-}Wei Chang and
                  Jiatong Shi and
                  Yifan Peng and
                  Roshan S. Sharma and
                  Shinji Watanabe and
                  Bhiksha Ramakrishnan and
                  Shady Shehata and
                  Hung{-}Yi Lee},
  title        = {Dynamic-Superb: Towards a Dynamic, Collaborative, and Comprehensive
                  Instruction-Tuning Benchmark For Speech},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
                  {ICASSP} 2024, Seoul, Republic of Korea, April 14-19, 2024},
  pages        = {12136--12140},
  publisher    = {{IEEE}},
  year         = {2024},
  url          = {https://doi.org/10.1109/ICASSP48485.2024.10448257},
  doi          = {10.1109/ICASSP48485.2024.10448257},
  timestamp    = {Sun, 04 Jan 2026 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/icassp/HuangLWHKWACSPS24.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/FutamiAKT024,
  author       = {Hayato Futami and
                  Siddhant Arora and
                  Yosuke Kashiwagi and
                  Emiru Tsunoo and
                  Shinji Watanabe},
  editor       = {Itshak Lapidot and
                  Sharon Gannot},
  title        = {Finding Task-specific Subnetworks in Multi-task Spoken Language Understanding
                  Model},
  booktitle    = {25th Annual Conference of the International Speech Communication Association,
                  Interspeech 2024, Kos, Greece, September 1-5, 2024},
  publisher    = {{ISCA}},
  year         = {2024},
  url          = {https://doi.org/10.21437/Interspeech.2024-712},
  doi          = {10.21437/INTERSPEECH.2024-712},
  timestamp    = {Thu, 25 Dec 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/interspeech/FutamiAKT024.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/Jung0E0STAYC24,
  author       = {Jee{-}weon Jung and
                  Xin Wang and
                  Nicholas W. D. Evans and
                  Shinji Watanabe and
                  Hye{-}jin Shim and
                  Hemlata Tak and
                  Siddhant Arora and
                  Junichi Yamagishi and
                  Joon Son Chung},
  editor       = {Itshak Lapidot and
                  Sharon Gannot},
  title        = {To what extent can {ASV} systems naturally defend against spoofing
                  attacks?},
  booktitle    = {25th Annual Conference of the International Speech Communication Association,
                  Interspeech 2024, Kos, Greece, September 1-5, 2024},
  publisher    = {{ISCA}},
  year         = {2024},
  url          = {https://doi.org/10.21437/Interspeech.2024-1354},
  doi          = {10.21437/INTERSPEECH.2024-1354},
  timestamp    = {Thu, 25 Dec 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/interspeech/Jung0E0STAYC24.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KashiwagiFTA024,
  author       = {Yosuke Kashiwagi and
                  Hayato Futami and
                  Emiru Tsunoo and
                  Siddhant Arora and
                  Shinji Watanabe},
  editor       = {Itshak Lapidot and
                  Sharon Gannot},
  title        = {Rapid Language Adaptation for Multilingual {E2E} Speech Recognition
                  Using Encoder Prompting},
  booktitle    = {25th Annual Conference of the International Speech Communication Association,
                  Interspeech 2024, Kos, Greece, September 1-5, 2024},
  publisher    = {{ISCA}},
  year         = {2024},
  url          = {https://doi.org/10.21437/Interspeech.2024-702},
  doi          = {10.21437/INTERSPEECH.2024-702},
  timestamp    = {Thu, 25 Dec 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/interspeech/KashiwagiFTA024.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/PengTCAYS0CSCJ024,
  author       = {Yifan Peng and
                  Jinchuan Tian and
                  William Chen and
                  Siddhant Arora and
                  Brian Yan and
                  Yui Sudo and
                  Muhammad Shakeel and
                  Kwanghee Choi and
                  Jiatong Shi and
                  Xuankai Chang and
                  Jee{-}weon Jung and
                  Shinji Watanabe},
  editor       = {Itshak Lapidot and
                  Sharon Gannot},
  title        = {{OWSM} v3.1: Better and Faster Open Whisper-Style Speech Models based
                  on E-Branchformer},
  booktitle    = {25th Annual Conference of the International Speech Communication Association,
                  Interspeech 2024, Kos, Greece, September 1-5, 2024},
  publisher    = {{ISCA}},
  year         = {2024},
  url          = {https://doi.org/10.21437/Interspeech.2024-1194},
  doi          = {10.21437/INTERSPEECH.2024-1194},
  timestamp    = {Thu, 25 Dec 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/interspeech/PengTCAYS0CSCJ024.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/TsunooFKA024,
  author       = {Emiru Tsunoo and
                  Hayato Futami and
                  Yosuke Kashiwagi and
                  Siddhant Arora and
                  Shinji Watanabe},
  editor       = {Itshak Lapidot and
                  Sharon Gannot},
  title        = {Decoder-only Architecture for Streaming End-to-end Speech Recognition},
  booktitle    = {25th Annual Conference of the International Speech Communication Association,
                  Interspeech 2024, Kos, Greece, September 1-5, 2024},
  publisher    = {{ISCA}},
  year         = {2024},
  url          = {https://doi.org/10.21437/Interspeech.2024-705},
  doi          = {10.21437/INTERSPEECH.2024-705},
  timestamp    = {Thu, 25 Dec 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/interspeech/TsunooFKA024.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/naacl/AroraFJPSKTL024,
  author       = {Siddhant Arora and
                  Hayato Futami and
                  Jee{-}weon Jung and
                  Yifan Peng and
                  Roshan S. Sharma and
                  Yosuke Kashiwagi and
                  Emiru Tsunoo and
                  Karen Livescu and
                  Shinji Watanabe},
  editor       = {Kevin Duh and
                  Helena G{\'{o}}mez{-}Adorno and
                  Steven Bethard},
  title        = {UniverSLU: Universal Spoken Language Understanding for Diverse Tasks
                  with Natural Language Instructions},
  booktitle    = {Proceedings of the 2024 Conference of the North American Chapter of
                  the Association for Computational Linguistics: Human Language Technologies
                  (Volume 1: Long Papers), {NAACL} 2024, Mexico City, Mexico, June 16-21,
                  2024},
  pages        = {2754--2774},
  publisher    = {Association for Computational Linguistics},
  year         = {2024},
  url          = {https://doi.org/10.18653/v1/2024.naacl-long.151},
  doi          = {10.18653/V1/2024.NAACL-LONG.151},
  timestamp    = {Thu, 25 Dec 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/naacl/AroraFJPSKTL024.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/slt/SomekiCACCHPSSW24,
  author       = {Masao Someki and
                  Kwanghee Choi and
                  Siddhant Arora and
                  William Chen and
                  Samuele Cornell and
                  Jionghao Han and
                  Yifan Peng and
                  Jiatong Shi and
                  Vaibhav Srivastav and
                  Shinji Watanabe},
  title        = {ESPnet-EZ: Python-Only ESPnet For Easy Fine-Tuning And Integration},
  booktitle    = {{IEEE} Spoken Language Technology Workshop, {SLT} 2024, Macao, December
                  2-5, 2024},
  pages        = {863--870},
  publisher    = {{IEEE}},
  year         = {2024},
  url          = {https://doi.org/10.1109/SLT61566.2024.10832148},
  doi          = {10.1109/SLT61566.2024.10832148},
  timestamp    = {Thu, 25 Dec 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/slt/SomekiCACCHPSSW24.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2401-16658,
  author       = {Yifan Peng and
                  Jinchuan Tian and
                  William Chen and
                  Siddhant Arora and
                  Brian Yan and
                  Yui Sudo and
                  Muhammad Shakeel and
                  Kwanghee Choi and
                  Jiatong Shi and
                  Xuankai Chang and
                  Jee{-}weon Jung and
                  Shinji Watanabe},
  title        = {{OWSM} v3.1: Better and Faster Open Whisper-Style Speech Models based
                  on E-Branchformer},
  journal      = {CoRR},
  volume       = {abs/2401.16658},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2401.16658},
  doi          = {10.48550/ARXIV.2401.16658},
  eprinttype   = {arXiv},
  eprint       = {2401.16658},
  timestamp    = {Fri, 27 Jun 2025 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2401-16658.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2402-16021,
  author       = {Minsu Kim and
                  Jee{-}weon Jung and
                  Hyeongseop Rha and
                  Soumi Maiti and
                  Siddhant Arora and
                  Xuankai Chang and
                  Shinji Watanabe and
                  Yong Man Ro},
  title        = {{TMT:} Tri-Modal Translation between Speech, Image, and Text by Processing
                  Different Modalities as Different Languages},
  journal      = {CoRR},
  volume       = {abs/2402.16021},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2402.16021},
  doi          = {10.48550/ARXIV.2402.16021},
  eprinttype   = {arXiv},
  eprint       = {2402.16021},
  timestamp    = {Mon, 03 Mar 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2402-16021.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2406-10083,
  author       = {Siddhant Arora and
                  Ankita Pasad and
                  Chung{-}Ming Chien and
                  Jionghao Han and
                  Roshan S. Sharma and
                  Jee{-}weon Jung and
                  Hira Dhamyal and
                  William Chen and
                  Suwon Shon and
                  Hung{-}yi Lee and
                  Karen Livescu and
                  Shinji Watanabe},
  title        = {On the Evaluation of Speech Foundation Models for Spoken Language
                  Understanding},
  journal      = {CoRR},
  volume       = {abs/2406.10083},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2406.10083},
  doi          = {10.48550/ARXIV.2406.10083},
  eprinttype   = {arXiv},
  eprint       = {2406.10083},
  timestamp    = {Thu, 25 Dec 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2406-10083.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2406-12317,
  author       = {Hayato Futami and
                  Siddhant Arora and
                  Yosuke Kashiwagi and
                  Emiru Tsunoo and
                  Shinji Watanabe},
  title        = {Finding Task-specific Subnetworks in Multi-task Spoken Language Understanding
                  Model},
  journal      = {CoRR},
  volume       = {abs/2406.12317},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2406.12317},
  doi          = {10.48550/ARXIV.2406.12317},
  eprinttype   = {arXiv},
  eprint       = {2406.12317},
  timestamp    = {Thu, 25 Dec 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2406-12317.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2406-12611,
  author       = {Yosuke Kashiwagi and
                  Hayato Futami and
                  Emiru Tsunoo and
                  Siddhant Arora and
                  Shinji Watanabe},
  title        = {Rapid Language Adaptation for Multilingual {E2E} Speech Recognition
                  Using Encoder Prompting},
  journal      = {CoRR},
  volume       = {abs/2406.12611},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2406.12611},
  doi          = {10.48550/ARXIV.2406.12611},
  eprinttype   = {arXiv},
  eprint       = {2406.12611},
  timestamp    = {Thu, 25 Dec 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2406-12611.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2406-16107,
  author       = {Emiru Tsunoo and
                  Hayato Futami and
                  Yosuke Kashiwagi and
                  Siddhant Arora and
                  Shinji Watanabe},
  title        = {Decoder-only Architecture for Streaming End-to-end Speech Recognition},
  journal      = {CoRR},
  volume       = {abs/2406.16107},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2406.16107},
  doi          = {10.48550/ARXIV.2406.16107},
  eprinttype   = {arXiv},
  eprint       = {2406.16107},
  timestamp    = {Thu, 25 Dec 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2406-16107.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2409-09506,
  author       = {Masao Someki and
                  Kwanghee Choi and
                  Siddhant Arora and
                  William Chen and
                  Samuele Cornell and
                  Jionghao Han and
                  Yifan Peng and
                  Jiatong Shi and
                  Vaibhav Srivastav and
                  Shinji Watanabe},
  title        = {ESPnet-EZ: Python-only ESPnet for Easy Fine-tuning and Integration},
  journal      = {CoRR},
  volume       = {abs/2409.09506},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2409.09506},
  doi          = {10.48550/ARXIV.2409.09506},
  eprinttype   = {arXiv},
  eprint       = {2409.09506},
  timestamp    = {Thu, 25 Dec 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2409-09506.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2409-11274,
  author       = {Yao{-}Fei Cheng and
                  Hayato Futami and
                  Yosuke Kashiwagi and
                  Emiru Tsunoo and
                  Wen Shen Teo and
                  Siddhant Arora and
                  Shinji Watanabe},
  title        = {Task Arithmetic for Language Expansion in Speech Translation},
  journal      = {CoRR},
  volume       = {abs/2409.11274},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2409.11274},
  doi          = {10.48550/ARXIV.2409.11274},
  eprinttype   = {arXiv},
  eprint       = {2409.11274},
  timestamp    = {Thu, 25 Dec 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2409-11274.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2409-15732,
  author       = {Yosuke Kashiwagi and
                  Hayato Futami and
                  Emiru Tsunoo and
                  Siddhant Arora and
                  Shinji Watanabe},
  title        = {Hypothesis Clustering and Merging: Novel MultiTalker Speech Recognition
                  with Speaker Tokens},
  journal      = {CoRR},
  volume       = {abs/2409.15732},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2409.15732},
  doi          = {10.48550/ARXIV.2409.15732},
  eprinttype   = {arXiv},
  eprint       = {2409.15732},
  timestamp    = {Thu, 25 Dec 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2409-15732.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2411-05361,
  author       = {Chien{-}yu Huang and
                  Wei{-}Chih Chen and
                  Shu{-}Wen Yang and
                  Andy T. Liu and
                  Chen{-}An Li and
                  Yu{-}Xiang Lin and
                  Wei{-}Cheng Tseng and
                  Anuj Diwan and
                  Yi{-}Jen Shih and
                  Jiatong Shi and
                  William Chen and
                  Xuanjun Chen and
                  Chi{-}Yuan Hsiao and
                  Puyuan Peng and
                  Shih{-}Heng Wang and
                  Chun{-}Yi Kuan and
                  Ke{-}Han Lu and
                  Kai{-}Wei Chang and
                  Chih{-}Kai Yang and
                  Fabian Ritter Gutierrez and
                  Ming To Chuang and
                  Kuan{-}Po Huang and
                  Siddhant Arora and
                  You{-}Kuan Lin and
                  Eunjung Yeo and
                  Kalvin Chang and
                  Chung{-}Ming Chien and
                  Kwanghee Choi and
                  Cheng{-}Hsiu Hsieh and
                  Yi{-}Cheng Lin and
                  Chee{-}En Yu and
                  I{-}Hsiang Chiu and
                  Heitor R. Guimar{\~{a}}es and
                  Jionghao Han and
                  Tzu{-}Quan Lin and
                  Tzu{-}Yuan Lin and
                  Homu Chang and
                  Ting{-}Wu Chang and
                  Chun Wei Chen and
                  Shou{-}Jen Chen and
                  Yu{-}Hua Chen and
                  Hsi{-}Chun Cheng and
                  Kunal Dhawan and
                  Jia{-}Lin Fang and
                  Shi{-}Xin Fang and
                  Kuan{-}Yu Fang Chiang and
                  Chi An Fu and
                  Hsien{-}Fu Hsiao and
                  Ching Yu Hsu and
                  Shao{-}Syuan Huang and
                  Lee Chen Wei and
                  Hsi{-}Che Lin and
                  Hsuan{-}Hao Lin and
                  Hsuan{-}Ting Lin and
                  Jian{-}Ren Lin and
                  Ting{-}Chun Liu and
                  Li{-}Chun Lu and
                  Tsung{-}Min Pai and
                  Ankita Pasad and
                  Shih{-}Yun Shan Kuan and
                  Suwon Shon and
                  Yuxun Tang and
                  Yun{-}Shao Tsai and
                  Jui{-}Chiang Wei and
                  Tzu{-}Chieh Wei and
                  Chengxi Wu and
                  Dien{-}Ruei Wu and
                  Chao{-}Han Huck Yang and
                  Chieh{-}Chi Yang and
                  Jia Qi Yip and
                  Shao{-}Xiang Yuan and
                  Vahid Noroozi and
                  Zhehuai Chen and
                  Haibin Wu and
                  Karen Livescu and
                  David Harwath and
                  Shinji Watanabe and
                  Hung{-}yi Lee},
  title        = {Dynamic-SUPERB Phase-2: {A} Collaboratively Expanding Benchmark for
                  Measuring the Capabilities of Spoken Language Models with 180 Tasks},
  journal      = {CoRR},
  volume       = {abs/2411.05361},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2411.05361},
  doi          = {10.48550/ARXIV.2411.05361},
  eprinttype   = {arXiv},
  eprint       = {2411.05361},
  timestamp    = {Sun, 04 Jan 2026 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2411-05361.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2412-17667,
  author       = {Jiatong Shi and
                  Hye{-}jin Shim and
                  Jinchuan Tian and
                  Siddhant Arora and
                  Haibin Wu and
                  Darius Petermann and
                  Jia Qi Yip and
                  You Zhang and
                  Yuxun Tang and
                  Wangyou Zhang and
                  Dareen Alharthi and
                  Yichen Huang and
                  Koichi Saito and
                  Jionghao Han and
                  Yiwen Zhao and
                  Chris Donahue and
                  Shinji Watanabe},
  title        = {{VERSA:} {A} Versatile Evaluation Toolkit for Speech, Audio, and Music},
  journal      = {CoRR},
  volume       = {abs/2412.17667},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2412.17667},
  doi          = {10.48550/ARXIV.2412.17667},
  eprinttype   = {arXiv},
  eprint       = {2412.17667},
  timestamp    = {Thu, 25 Dec 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2412-17667.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/acl/ShonALPWSWLL023,
  author       = {Suwon Shon and
                  Siddhant Arora and
                  Chyi{-}Jiunn Lin and
                  Ankita Pasad and
                  Felix Wu and
                  Roshan S. Sharma and
                  Wei{-}Lun Wu and
                  Hung{-}yi Lee and
                  Karen Livescu and
                  Shinji Watanabe},
  editor       = {Anna Rogers and
                  Jordan L. Boyd{-}Graber and
                  Naoaki Okazaki},
  title        = {{SLUE} Phase-2: {A} Benchmark Suite of Diverse Spoken Language Understanding
                  Tasks},
  booktitle    = {Proceedings of the 61st Annual Meeting of the Association for Computational
                  Linguistics (Volume 1: Long Papers), {ACL} 2023, Toronto, Canada,
                  July 9-14, 2023},
  pages        = {8906--8937},
  publisher    = {Association for Computational Linguistics},
  year         = {2023},
  url          = {https://doi.org/10.18653/v1/2023.acl-long.496},
  doi          = {10.18653/V1/2023.ACL-LONG.496},
  timestamp    = {Sun, 19 Jan 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/acl/ShonALPWSWLL023.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/PengTYBCLSACSZSSJMW23,
  author       = {Yifan Peng and
                  Jinchuan Tian and
                  Brian Yan and
                  Dan Berrebbi and
                  Xuankai Chang and
                  Xinjian Li and
                  Jiatong Shi and
                  Siddhant Arora and
                  William Chen and
                  Roshan S. Sharma and
                  Wangyou Zhang and
                  Yui Sudo and
                  Muhammad Shakeel and
                  Jee{-}Weon Jung and
                  Soumi Maiti and
                  Shinji Watanabe},
  title        = {Reproducing Whisper-Style Training Using An Open-Source Toolkit And
                  Publicly Available Data},
  booktitle    = {{IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU}
                  2023, Taipei, Taiwan, December 16-20, 2023},
  pages        = {1--8},
  publisher    = {{IEEE}},
  year         = {2023},
  url          = {https://doi.org/10.1109/ASRU57964.2023.10389676},
  doi          = {10.1109/ASRU57964.2023.10389676},
  timestamp    = {Fri, 27 Jun 2025 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/asru/PengTYBCLSACSZSSJMW23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/SharmaCKSAWODSR23,
  author       = {Roshan S. Sharma and
                  William Chen and
                  Takatomo Kano and
                  Ruchira Sharma and
                  Siddhant Arora and
                  Shinji Watanabe and
                  Atsunori Ogawa and
                  Marc Delcroix and
                  Rita Singh and
                  Bhiksha Raj},
  title        = {Espnet-Summ: Introducing a Novel Large Dataset, Toolkit, and a Cross-Corpora
                  Evaluation of Speech Summarization Systems},
  booktitle    = {{IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU}
                  2023, Taipei, Taiwan, December 16-20, 2023},
  pages        = {1--8},
  publisher    = {{IEEE}},
  year         = {2023},
  url          = {https://doi.org/10.1109/ASRU57964.2023.10389641},
  doi          = {10.1109/ASRU57964.2023.10389641},
  timestamp    = {Mon, 03 Mar 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/asru/SharmaCKSAWODSR23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/comad/GaurSAGB23,
  author       = {Garima Gaur and
                  Rajat Singh and
                  Siddhant Arora and
                  Vinayak Gupta and
                  Srikanta Bedathur},
  title        = {Teaching Old {DB} Neu(ral) Tricks: Learning Embeddings on Multi-tabular
                  Databases},
  booktitle    = {Proceedings of the 6th Joint International Conference on Data Science
                  {\&} Management of Data (10th {ACM} {IKDD} {CODS} and 28th COMAD),
                  Mumbai, India, January 4-7, 2023},
  pages        = {87--94},
  publisher    = {{ACM}},
  year         = {2023},
  url          = {https://doi.org/10.1145/3570991.3571041},
  doi          = {10.1145/3570991.3571041},
  timestamp    = {Sun, 19 Jan 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/comad/GaurSAGB23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/AroraFTYW23,
  author       = {Siddhant Arora and
                  Hayato Futami and
                  Emiru Tsunoo and
                  Brian Yan and
                  Shinji Watanabe},
  title        = {Joint Modelling of Spoken Language Understanding Tasks with Integrated
                  Dialog History},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing
                  {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
  pages        = {1--5},
  publisher    = {{IEEE}},
  year         = {2023},
  url          = {https://doi.org/10.1109/ICASSP49357.2023.10095055},
  doi          = {10.1109/ICASSP49357.2023.10095055},
  timestamp    = {Mon, 03 Mar 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/icassp/AroraFTYW23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/AroraFWHPKTYW23,
  author       = {Siddhant Arora and
                  Hayato Futami and
                  Shih{-}Lun Wu and
                  Jessica Huynh and
                  Yifan Peng and
                  Yosuke Kashiwagi and
                  Emiru Tsunoo and
                  Brian Yan and
                  Shinji Watanabe},
  title        = {A Study on the Integration of Pipeline and {E2E} {SLU} Systems for
                  Spoken Semantic Parsing Toward Stop Quality Challenge},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing
                  {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
  pages        = {1--2},
  publisher    = {{IEEE}},
  year         = {2023},
  url          = {https://doi.org/10.1109/ICASSP49357.2023.10096175},
  doi          = {10.1109/ICASSP49357.2023.10096175},
  timestamp    = {Fri, 27 Jun 2025 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/AroraFWHPKTYW23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/FutamiHAWKPYTW23,
  author       = {Hayato Futami and
                  Jessica Huynh and
                  Siddhant Arora and
                  Shih{-}Lun Wu and
                  Yosuke Kashiwagi and
                  Yifan Peng and
                  Brian Yan and
                  Emiru Tsunoo and
                  Shinji Watanabe},
  title        = {The Pipeline System of {ASR} and {NLU} with MLM-based data Augmentation
                  Toward Stop Low-Resource Challenge},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing
                  {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
  pages        = {1--2},
  publisher    = {{IEEE}},
  year         = {2023},
  url          = {https://doi.org/10.1109/ICASSP49357.2023.10096049},
  doi          = {10.1109/ICASSP49357.2023.10096049},
  timestamp    = {Fri, 27 Jun 2025 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/FutamiHAWKPYTW23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/FutamiTSKOAW23,
  author       = {Hayato Futami and
                  Emiru Tsunoo and
                  Kentaro Shibata and
                  Yosuke Kashiwagi and
                  Takao Okuda and
                  Siddhant Arora and
                  Shinji Watanabe},
  title        = {Streaming Joint Speech Recognition and Disfluency Detection},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing
                  {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
  pages        = {1--5},
  publisher    = {{IEEE}},
  year         = {2023},
  url          = {https://doi.org/10.1109/ICASSP49357.2023.10094620},
  doi          = {10.1109/ICASSP49357.2023.10094620},
  timestamp    = {Mon, 03 Mar 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/icassp/FutamiTSKOAW23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KashiwagiAFHWPYTW23,
  author       = {Yosuke Kashiwagi and
                  Siddhant Arora and
                  Hayato Futami and
                  Jessica Huynh and
                  Shih{-}Lun Wu and
                  Yifan Peng and
                  Brian Yan and
                  Emiru Tsunoo and
                  Shinji Watanabe},
  title        = {E-Branchformer-Based {E2E} {SLU} Toward Stop on-Device Challenge},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing
                  {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
  pages        = {1--2},
  publisher    = {{IEEE}},
  year         = {2023},
  url          = {https://doi.org/10.1109/ICASSP49357.2023.10097145},
  doi          = {10.1109/ICASSP49357.2023.10097145},
  timestamp    = {Fri, 27 Jun 2025 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/KashiwagiAFHWPYTW23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KashiwagiAFHWPY23,
  author       = {Yosuke Kashiwagi and
                  Siddhant Arora and
                  Hayato Futami and
                  Jessica Huynh and
                  Shih{-}Lun Wu and
                  Yifan Peng and
                  Brian Yan and
                  Emiru Tsunoo and
                  Shinji Watanabe},
  editor       = {Naomi Harte and
                  Julie Carson{-}Berndsen and
                  Gareth Jones},
  title        = {Tensor decomposition for minimization of {E2E} {SLU} model toward
                  on-device processing},
  booktitle    = {24th Annual Conference of the International Speech Communication Association,
                  Interspeech 2023, Dublin, Ireland, August 20-24, 2023},
  pages        = {710--714},
  publisher    = {{ISCA}},
  year         = {2023},
  url          = {https://doi.org/10.21437/Interspeech.2023-1299},
  doi          = {10.21437/INTERSPEECH.2023-1299},
  timestamp    = {Fri, 27 Jun 2025 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/KashiwagiAFHWPY23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/AroraFKTY023,
  author       = {Siddhant Arora and
                  Hayato Futami and
                  Yosuke Kashiwagi and
                  Emiru Tsunoo and
                  Brian Yan and
                  Shinji Watanabe},
  editor       = {Naomi Harte and
                  Julie Carson{-}Berndsen and
                  Gareth Jones},
  title        = {Integrating Pretrained {ASR} and {LM} to Perform Sequence Generation
                  for Spoken Language Understanding},
  booktitle    = {24th Annual Conference of the International Speech Communication Association,
                  Interspeech 2023, Dublin, Ireland, August 20-24, 2023},
  pages        = {720--724},
  publisher    = {{ISCA}},
  year         = {2023},
  url          = {https://doi.org/10.21437/Interspeech.2023-1962},
  doi          = {10.21437/INTERSPEECH.2023-1962},
  timestamp    = {Mon, 03 Mar 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/interspeech/AroraFKTY023.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/TsunooFKA023,
  author       = {Emiru Tsunoo and
                  Hayato Futami and
                  Yosuke Kashiwagi and
                  Siddhant Arora and
                  Shinji Watanabe},
  editor       = {Naomi Harte and
                  Julie Carson{-}Berndsen and
                  Gareth Jones},
  title        = {Integration of Frame- and Label-synchronous Beam Search for Streaming
                  Encoder-decoder Speech Recognition},
  booktitle    = {24th Annual Conference of the International Speech Communication Association,
                  Interspeech 2023, Dublin, Ireland, August 20-24, 2023},
  pages        = {1369--1373},
  publisher    = {{ISCA}},
  year         = {2023},
  url          = {https://doi.org/10.21437/Interspeech.2023-1517},
  doi          = {10.21437/INTERSPEECH.2023-1517},
  timestamp    = {Mon, 03 Mar 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/interspeech/TsunooFKA023.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/0001AZ0SR23,
  author       = {Roshan Sharma and
                  Siddhant Arora and
                  Kenneth Zheng and
                  Shinji Watanabe and
                  Rita Singh and
                  Bhiksha Raj},
  editor       = {Naomi Harte and
                  Julie Carson{-}Berndsen and
                  Gareth Jones},
  title        = {{BASS:} Block-wise Adaptation for Speech Summarization},
  booktitle    = {24th Annual Conference of the International Speech Communication Association,
                  Interspeech 2023, Dublin, Ireland, August 20-24, 2023},
  pages        = {1454--1458},
  publisher    = {{ISCA}},
  year         = {2023},
  url          = {https://doi.org/10.21437/Interspeech.2023-916},
  doi          = {10.21437/INTERSPEECH.2023-916},
  timestamp    = {Mon, 03 Mar 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/interspeech/0001AZ0SR23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/PengKWYACTSS023,
  author       = {Yifan Peng and
                  Kwangyoun Kim and
                  Felix Wu and
                  Brian Yan and
                  Siddhant Arora and
                  William Chen and
                  Jiyang Tang and
                  Suwon Shon and
                  Prashant Sridhar and
                  Shinji Watanabe},
  editor       = {Naomi Harte and
                  Julie Carson{-}Berndsen and
                  Gareth Jones},
  title        = {A Comparative Study on E-Branchformer vs Conformer in Speech Recognition,
                  Translation, and Understanding Tasks},
  booktitle    = {24th Annual Conference of the International Speech Communication Association,
                  Interspeech 2023, Dublin, Ireland, August 20-24, 2023},
  pages        = {2208--2212},
  publisher    = {{ISCA}},
  year         = {2023},
  url          = {https://doi.org/10.21437/Interspeech.2023-1194},
  doi          = {10.21437/INTERSPEECH.2023-1194},
  timestamp    = {Fri, 27 Jun 2025 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/PengKWYACTSS023.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iwslt/YanSMCLPA023,
  author       = {Brian Yan and
                  Jiatong Shi and
                  Soumi Maiti and
                  William Chen and
                  Xinjian Li and
                  Yifan Peng and
                  Siddhant Arora and
                  Shinji Watanabe},
  editor       = {Elizabeth Salesky and
                  Marcello Federico and
                  Marine Carpuat},
  title        = {CMU's {IWSLT} 2023 Simultaneous Speech Translation System},
  booktitle    = {Proceedings of the 20th International Conference on Spoken Language
                  Translation, IWSLT@ACL 2023, Toronto, Canada (in-person and online),
                  13-14 July, 2023},
  pages        = {235--240},
  publisher    = {Association for Computational Linguistics},
  year         = {2023},
  url          = {https://doi.org/10.18653/v1/2023.iwslt-1.20},
  doi          = {10.18653/V1/2023.IWSLT-1.20},
  timestamp    = {Fri, 27 Jun 2025 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/iwslt/YanSMCLPA023.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-00926,
  author       = {Siddhant Arora and
                  Hayato Futami and
                  Emiru Tsunoo and
                  Brian Yan and
                  Shinji Watanabe},
  title        = {Joint Modelling of Spoken Language Understanding Tasks with Integrated
                  Dialog History},
  journal      = {CoRR},
  volume       = {abs/2305.00926},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2305.00926},
  doi          = {10.48550/ARXIV.2305.00926},
  eprinttype   = {arXiv},
  eprint       = {2305.00926},
  timestamp    = {Mon, 03 Mar 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2305-00926.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-01194,
  author       = {Hayato Futami and
                  Jessica Huynh and
                  Siddhant Arora and
                  Shih{-}Lun Wu and
                  Yosuke Kashiwagi and
                  Yifan Peng and
                  Brian Yan and
                  Emiru Tsunoo and
                  Shinji Watanabe},
  title        = {The Pipeline System of {ASR} and {NLU} with MLM-based Data Augmentation
                  toward {STOP} Low-resource Challenge},
  journal      = {CoRR},
  volume       = {abs/2305.01194},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2305.01194},
  doi          = {10.48550/ARXIV.2305.01194},
  eprinttype   = {arXiv},
  eprint       = {2305.01194},
  timestamp    = {Fri, 27 Jun 2025 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2305-01194.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-01620,
  author       = {Siddhant Arora and
                  Hayato Futami and
                  Shih{-}Lun Wu and
                  Jessica Huynh and
                  Yifan Peng and
                  Yosuke Kashiwagi and
                  Emiru Tsunoo and
                  Brian Yan and
                  Shinji Watanabe},
  title        = {A Study on the Integration of Pipeline and {E2E} {SLU} systems for
                  Spoken Semantic Parsing toward {STOP} Quality Challenge},
  journal      = {CoRR},
  volume       = {abs/2305.01620},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2305.01620},
  doi          = {10.48550/ARXIV.2305.01620},
  eprinttype   = {arXiv},
  eprint       = {2305.01620},
  timestamp    = {Fri, 27 Jun 2025 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2305-01620.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-11073,
  author       = {Yifan Peng and
                  Kwangyoun Kim and
                  Felix Wu and
                  Brian Yan and
                  Siddhant Arora and
                  William Chen and
                  Jiyang Tang and
                  Suwon Shon and
                  Prashant Sridhar and
                  Shinji Watanabe},
  title        = {A Comparative Study on E-Branchformer vs Conformer in Speech Recognition,
                  Translation, and Understanding Tasks},
  journal      = {CoRR},
  volume       = {abs/2305.11073},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2305.11073},
  doi          = {10.48550/ARXIV.2305.11073},
  eprinttype   = {arXiv},
  eprint       = {2305.11073},
  timestamp    = {Fri, 27 Jun 2025 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2305-11073.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2307-08217,
  author       = {Roshan S. Sharma and
                  Kenneth Zheng and
                  Siddhant Arora and
                  Shinji Watanabe and
                  Rita Singh and
                  Bhiksha Raj},
  title        = {{BASS:} Block-wise Adaptation for Speech Summarization},
  journal      = {CoRR},
  volume       = {abs/2307.08217},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2307.08217},
  doi          = {10.48550/ARXIV.2307.08217},
  eprinttype   = {arXiv},
  eprint       = {2307.08217},
  timestamp    = {Wed, 26 Jul 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2307-08217.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2307-11005,
  author       = {Siddhant Arora and
                  Hayato Futami and
                  Yosuke Kashiwagi and
                  Emiru Tsunoo and
                  Brian Yan and
                  Shinji Watanabe},
  title        = {Integrating Pretrained {ASR} and {LM} to Perform Sequence Generation
                  for Spoken Language Understanding},
  journal      = {CoRR},
  volume       = {abs/2307.11005},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2307.11005},
  doi          = {10.48550/ARXIV.2307.11005},
  eprinttype   = {arXiv},
  eprint       = {2307.11005},
  timestamp    = {Wed, 26 Jul 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2307-11005.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2307-12767,
  author       = {Emiru Tsunoo and
                  Hayato Futami and
                  Yosuke Kashiwagi and
                  Siddhant Arora and
                  Shinji Watanabe},
  title        = {Integration of Frame- and Label-synchronous Beam Search for Streaming
                  Encoder-decoder Speech Recognition},
  journal      = {CoRR},
  volume       = {abs/2307.12767},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2307.12767},
  doi          = {10.48550/ARXIV.2307.12767},
  eprinttype   = {arXiv},
  eprint       = {2307.12767},
  timestamp    = {Tue, 01 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2307-12767.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2309-08876,
  author       = {Emiru Tsunoo and
                  Hayato Futami and
                  Yosuke Kashiwagi and
                  Siddhant Arora and
                  Shinji Watanabe},
  title        = {Decoder-only Architecture for Speech Recognition with {CTC} Prompts
                  and Text Data Augmentation},
  journal      = {CoRR},
  volume       = {abs/2309.08876},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2309.08876},
  doi          = {10.48550/ARXIV.2309.08876},
  eprinttype   = {arXiv},
  eprint       = {2309.08876},
  timestamp    = {Mon, 03 Mar 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2309-08876.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2309-09510,
  author       = {Chien{-}yu Huang and
                  Ke{-}Han Lu and
                  Shih{-}Heng Wang and
                  Chi{-}Yuan Hsiao and
                  Chun{-}Yi Kuan and
                  Haibin Wu and
                  Siddhant Arora and
                  Kai{-}Wei Chang and
                  Jiatong Shi and
                  Yifan Peng and
                  Roshan S. Sharma and
                  Shinji Watanabe and
                  Bhiksha Ramakrishnan and
                  Shady Shehata and
                  Hung{-}yi Lee},
  title        = {Dynamic-SUPERB: Towards {A} Dynamic, Collaborative, and Comprehensive
                  Instruction-Tuning Benchmark for Speech},
  journal      = {CoRR},
  volume       = {abs/2309.09510},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2309.09510},
  doi          = {10.48550/ARXIV.2309.09510},
  eprinttype   = {arXiv},
  eprint       = {2309.09510},
  timestamp    = {Thu, 25 Dec 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2309-09510.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2309-10926,
  author       = {Siddhant Arora and
                  George Saon and
                  Shinji Watanabe and
                  Brian Kingsbury},
  title        = {Semi-Autoregressive Streaming {ASR} With Label Context},
  journal      = {CoRR},
  volume       = {abs/2309.10926},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2309.10926},
  doi          = {10.48550/ARXIV.2309.10926},
  eprinttype   = {arXiv},
  eprint       = {2309.10926},
  timestamp    = {Mon, 03 Mar 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2309-10926.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2309-13876,
  author       = {Yifan Peng and
                  Jinchuan Tian and
                  Brian Yan and
                  Dan Berrebbi and
                  Xuankai Chang and
                  Xinjian Li and
                  Jiatong Shi and
                  Siddhant Arora and
                  William Chen and
                  Roshan S. Sharma and
                  Wangyou Zhang and
                  Yui Sudo and
                  Muhammad Shakeel and
                  Jee{-}weon Jung and
                  Soumi Maiti and
                  Shinji Watanabe},
  title        = {Reproducing Whisper-Style Training Using an Open-Source Toolkit and
                  Publicly Available Data},
  journal      = {CoRR},
  volume       = {abs/2309.13876},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2309.13876},
  doi          = {10.48550/ARXIV.2309.13876},
  eprinttype   = {arXiv},
  eprint       = {2309.13876},
  timestamp    = {Fri, 27 Jun 2025 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2309-13876.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2310-02973,
  author       = {Siddhant Arora and
                  Hayato Futami and
                  Jee{-}weon Jung and
                  Yifan Peng and
                  Roshan S. Sharma and
                  Yosuke Kashiwagi and
                  Emiru Tsunoo and
                  Shinji Watanabe},
  title        = {UniverSLU: Universal Spoken Language Understanding for Diverse Classification
                  and Sequence Generation Tasks with a Single Network},
  journal      = {CoRR},
  volume       = {abs/2310.02973},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2310.02973},
  doi          = {10.48550/ARXIV.2310.02973},
  eprinttype   = {arXiv},
  eprint       = {2310.02973},
  timestamp    = {Mon, 30 Jun 2025 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2310-02973.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2312-09582,
  author       = {Hayato Futami and
                  Emiru Tsunoo and
                  Yosuke Kashiwagi and
                  Hiroaki Ogawa and
                  Siddhant Arora and
                  Shinji Watanabe},
  title        = {Phoneme-aware Encoding for Prefix-tree-based Contextual {ASR}},
  journal      = {CoRR},
  volume       = {abs/2312.09582},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2312.09582},
  doi          = {10.48550/ARXIV.2312.09582},
  eprinttype   = {arXiv},
  eprint       = {2312.09582},
  timestamp    = {Mon, 03 Mar 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2312-09582.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/AroraPSCLN22,
  author       = {Siddhant Arora and
                  Danish Pruthi and
                  Norman M. Sadeh and
                  William W. Cohen and
                  Zachary C. Lipton and
                  Graham Neubig},
  title        = {Explain, Edit, and Understand: Rethinking User Study Design for Evaluating
                  Model Explanations},
  booktitle    = {Thirty-Sixth {AAAI} Conference on Artificial Intelligence, {AAAI}
                  2022, Thirty-Fourth Conference on Innovative Applications of Artificial
                  Intelligence, {IAAI} 2022, The Twelveth Symposium on Educational Advances
                  in Artificial Intelligence, {EAAI} 2022 Virtual Event, February 22
                  - March 1, 2022},
  pages        = {5277--5285},
  publisher    = {{AAAI} Press},
  year         = {2022},
  url          = {https://doi.org/10.1609/aaai.v36i5.20464},
  doi          = {10.1609/AAAI.V36I5.20464},
  timestamp    = {Wed, 18 Mar 2026 17:07:12 +0100},
  biburl       = {https://dblp.org/rec/conf/aaai/AroraPSCLN22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/emnlp/AroraDYMB022,
  author       = {Siddhant Arora and
                  Siddharth Dalmia and
                  Brian Yan and
                  Florian Metze and
                  Alan W. Black and
                  Shinji Watanabe},
  editor       = {Yoav Goldberg and
                  Zornitsa Kozareva and
                  Yue Zhang},
  title        = {Token-level Sequence Labeling for Spoken Language Understanding using
                  Compositional End-to-End Models},
  booktitle    = {Findings of the Association for Computational Linguistics: {EMNLP}
                  2022, Abu Dhabi, United Arab Emirates, December 7-11, 2022},
  series       = {Findings of {ACL}},
  pages        = {5419--5429},
  publisher    = {Association for Computational Linguistics},
  year         = {2022},
  url          = {https://doi.org/10.18653/v1/2022.findings-emnlp.396},
  doi          = {10.18653/V1/2022.FINDINGS-EMNLP.396},
  timestamp    = {Tue, 27 Jan 2026 20:14:34 +0100},
  biburl       = {https://dblp.org/rec/conf/emnlp/AroraDYMB022.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/emnlp/HiguchiYAOK022,
  author       = {Yosuke Higuchi and
                  Brian Yan and
                  Siddhant Arora and
                  Tetsuji Ogawa and
                  Tetsunori Kobayashi and
                  Shinji Watanabe},
  editor       = {Yoav Goldberg and
                  Zornitsa Kozareva and
                  Yue Zhang},
  title        = {{BERT} Meets {CTC:} New Formulation of End-to-End Speech Recognition
                  with Pre-trained Masked Language Model},
  booktitle    = {Findings of the Association for Computational Linguistics: {EMNLP}
                  2022, Abu Dhabi, United Arab Emirates, December 7-11, 2022},
  series       = {Findings of {ACL}},
  pages        = {5486--5503},
  publisher    = {Association for Computational Linguistics},
  year         = {2022},
  url          = {https://doi.org/10.18653/v1/2022.findings-emnlp.402},
  doi          = {10.18653/V1/2022.FINDINGS-EMNLP.402},
  timestamp    = {Thu, 10 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/emnlp/HiguchiYAOK022.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/AroraDDCUPZKGYV22,
  author       = {Siddhant Arora and
                  Siddharth Dalmia and
                  Pavel Denisov and
                  Xuankai Chang and
                  Yushi Ueda and
                  Yifan Peng and
                  Yuekai Zhang and
                  Sujay Kumar and
                  Karthik Ganesan and
                  Brian Yan and
                  Ngoc Thang Vu and
                  Alan W. Black and
                  Shinji Watanabe},
  title        = {ESPnet-SLU: Advancing Spoken Language Understanding Through ESPnet},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
                  {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
  pages        = {7167--7171},
  publisher    = {{IEEE}},
  year         = {2022},
  url          = {https://doi.org/10.1109/ICASSP43922.2022.9747674},
  doi          = {10.1109/ICASSP43922.2022.9747674},
  timestamp    = {Fri, 27 Jun 2025 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/AroraDDCUPZKGYV22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/Deng0SA22,
  author       = {Keqi Deng and
                  Shinji Watanabe and
                  Jiatong Shi and
                  Siddhant Arora},
  editor       = {Hanseok Ko and
                  John H. L. Hansen},
  title        = {Blockwise Streaming Transformer for Spoken Language Understanding
                  and Simultaneous Speech Translation},
  booktitle    = {23rd Annual Conference of the International Speech Communication Association,
                  Interspeech 2022, Incheon, Korea, September 18-22, 2022},
  pages        = {1746--1750},
  publisher    = {{ISCA}},
  year         = {2022},
  url          = {https://doi.org/10.21437/Interspeech.2022-933},
  doi          = {10.21437/INTERSPEECH.2022-933},
  timestamp    = {Tue, 11 Jun 2024 16:45:43 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/Deng0SA22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/AroraDCYB022,
  author       = {Siddhant Arora and
                  Siddharth Dalmia and
                  Xuankai Chang and
                  Brian Yan and
                  Alan W. Black and
                  Shinji Watanabe},
  editor       = {Hanseok Ko and
                  John H. L. Hansen},
  title        = {Two-Pass Low Latency End-to-End Spoken Language Understanding},
  booktitle    = {23rd Annual Conference of the International Speech Communication Association,
                  Interspeech 2022, Incheon, Korea, September 18-22, 2022},
  pages        = {3478--3482},
  publisher    = {{ISCA}},
  year         = {2022},
  url          = {https://doi.org/10.21437/Interspeech.2022-10890},
  doi          = {10.21437/INTERSPEECH.2022-10890},
  timestamp    = {Wed, 21 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/AroraDCYB022.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/lrec/AroraHUKDRSMCDN22,
  author       = {Siddhant Arora and
                  Henry Hosseini and
                  Christine Utz and
                  Vinayshekhar Bannihatti Kumar and
                  Tristan Dhellemmes and
                  Abhilasha Ravichander and
                  Peter Story and
                  Jasmine Mangat and
                  Rex Chen and
                  Martin Degeling and
                  Thomas B. Norton and
                  Thomas Hupperich and
                  Shomir Wilson and
                  Norman M. Sadeh},
  editor       = {Nicoletta Calzolari and
                  Fr{\'{e}}d{\'{e}}ric B{\'{e}}chet and
                  Philippe Blache and
                  Khalid Choukri and
                  Christopher Cieri and
                  Thierry Declerck and
                  Sara Goggi and
                  Hitoshi Isahara and
                  Bente Maegaard and
                  Joseph Mariani and
                  H{\'{e}}l{\`{e}}ne Mazo and
                  Jan Odijk and
                  Stelios Piperidis},
  title        = {A Tale of Two Regulatory Regimes: Creation and Analysis of a Bilingual
                  Privacy Policy Corpus},
  booktitle    = {Proceedings of the Thirteenth Language Resources and Evaluation Conference,
                  {LREC} 2022, Marseille, France, 20-25 June 2022},
  pages        = {5460--5472},
  publisher    = {European Language Resources Association},
  year         = {2022},
  url          = {https://aclanthology.org/2022.lrec-1.585},
  timestamp    = {Mon, 10 Oct 2022 16:57:52 +0200},
  biburl       = {https://dblp.org/rec/conf/lrec/AroraHUKDRSMCDN22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/slt/PengAHUKGDCW22,
  author       = {Yifan Peng and
                  Siddhant Arora and
                  Yosuke Higuchi and
                  Yushi Ueda and
                  Sujay Kumar and
                  Karthik Ganesan and
                  Siddharth Dalmia and
                  Xuankai Chang and
                  Shinji Watanabe},
  title        = {A Study on the Integration of Pre-Trained SSL, ASR, {LM} and {SLU}
                  Models for Spoken Language Understanding},
  booktitle    = {{IEEE} Spoken Language Technology Workshop, {SLT} 2022, Doha, Qatar,
                  January 9-12, 2023},
  pages        = {406--413},
  publisher    = {{IEEE}},
  year         = {2022},
  url          = {https://doi.org/10.1109/SLT54892.2023.10022399},
  doi          = {10.1109/SLT54892.2023.10022399},
  timestamp    = {Fri, 27 Jun 2025 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/slt/PengAHUKGDCW22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-08920,
  author       = {Keqi Deng and
                  Shinji Watanabe and
                  Jiatong Shi and
                  Siddhant Arora},
  title        = {Blockwise Streaming Transformer for Spoken Language Understanding
                  and Simultaneous Speech Translation},
  journal      = {CoRR},
  volume       = {abs/2204.08920},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2204.08920},
  doi          = {10.48550/ARXIV.2204.08920},
  eprinttype   = {arXiv},
  eprint       = {2204.08920},
  timestamp    = {Mon, 03 Mar 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2204-08920.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2206-14169,
  author       = {Sonu Gupta and
                  Ellen Poplavska and
                  Nora O'Toole and
                  Siddhant Arora and
                  Thomas B. Norton and
                  Norman M. Sadeh and
                  Shomir Wilson},
  title        = {Creation and Analysis of an International Corpus of Privacy Laws},
  journal      = {CoRR},
  volume       = {abs/2206.14169},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2206.14169},
  doi          = {10.48550/ARXIV.2206.14169},
  eprinttype   = {arXiv},
  eprint       = {2206.14169},
  timestamp    = {Mon, 04 Jul 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2206-14169.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2207-06670,
  author       = {Siddhant Arora and
                  Siddharth Dalmia and
                  Xuankai Chang and
                  Brian Yan and
                  Alan W. Black and
                  Shinji Watanabe},
  title        = {Two-Pass Low Latency End-to-End Spoken Language Understanding},
  journal      = {CoRR},
  volume       = {abs/2207.06670},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2207.06670},
  doi          = {10.48550/ARXIV.2207.06670},
  eprinttype   = {arXiv},
  eprint       = {2207.06670},
  timestamp    = {Tue, 21 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2207-06670.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-15734,
  author       = {Siddhant Arora and
                  Siddharth Dalmia and
                  Brian Yan and
                  Florian Metze and
                  Alan W. Black and
                  Shinji Watanabe},
  title        = {Token-level Sequence Labeling for Spoken Language Understanding using
                  Compositional End-to-End Models},
  journal      = {CoRR},
  volume       = {abs/2210.15734},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2210.15734},
  doi          = {10.48550/ARXIV.2210.15734},
  eprinttype   = {arXiv},
  eprint       = {2210.15734},
  timestamp    = {Tue, 21 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2210-15734.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-16663,
  author       = {Yosuke Higuchi and
                  Brian Yan and
                  Siddhant Arora and
                  Tetsuji Ogawa and
                  Tetsunori Kobayashi and
                  Shinji Watanabe},
  title        = {{BERT} Meets {CTC:} New Formulation of End-to-End Speech Recognition
                  with Pre-trained Masked Language Model},
  journal      = {CoRR},
  volume       = {abs/2210.16663},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2210.16663},
  doi          = {10.48550/ARXIV.2210.16663},
  eprinttype   = {arXiv},
  eprint       = {2210.16663},
  timestamp    = {Tue, 21 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2210-16663.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2211-05869,
  author       = {Yifan Peng and
                  Siddhant Arora and
                  Yosuke Higuchi and
                  Yushi Ueda and
                  Sujay Kumar and
                  Karthik Ganesan and
                  Siddharth Dalmia and
                  Xuankai Chang and
                  Shinji Watanabe},
  title        = {A Study on the Integration of Pre-trained SSL, ASR, {LM} and {SLU}
                  Models for Spoken Language Understanding},
  journal      = {CoRR},
  volume       = {abs/2211.05869},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2211.05869},
  doi          = {10.48550/ARXIV.2211.05869},
  eprinttype   = {arXiv},
  eprint       = {2211.05869},
  timestamp    = {Fri, 27 Jun 2025 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2211-05869.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2211-08726,
  author       = {Hayato Futami and
                  Emiru Tsunoo and
                  Kentaro Shibata and
                  Yosuke Kashiwagi and
                  Takao Okuda and
                  Siddhant Arora and
                  Shinji Watanabe},
  title        = {Streaming Joint Speech Recognition and Disfluency Detection},
  journal      = {CoRR},
  volume       = {abs/2211.08726},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2211.08726},
  doi          = {10.48550/ARXIV.2211.08726},
  eprinttype   = {arXiv},
  eprint       = {2211.08726},
  timestamp    = {Tue, 21 Mar 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2211-08726.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2212-10525,
  author       = {Suwon Shon and
                  Siddhant Arora and
                  Chyi{-}Jiunn Lin and
                  Ankita Pasad and
                  Felix Wu and
                  Roshan S. Sharma and
                  Wei{-}Lun Wu and
                  Hung{-}Yi Lee and
                  Karen Livescu and
                  Shinji Watanabe},
  title        = {{SLUE} Phase-2: {A} Benchmark Suite of Diverse Spoken Language Understanding
                  Tasks},
  journal      = {CoRR},
  volume       = {abs/2212.10525},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2212.10525},
  doi          = {10.48550/ARXIV.2212.10525},
  eprinttype   = {arXiv},
  eprint       = {2212.10525},
  timestamp    = {Thu, 13 Jul 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2212-10525.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/AroraO0DM0B21,
  author       = {Siddhant Arora and
                  Alissa Ostapenko and
                  Vijay Viswanathan and
                  Siddharth Dalmia and
                  Florian Metze and
                  Shinji Watanabe and
                  Alan W. Black},
  editor       = {Hynek Hermansky and
                  Honza Cernock{\'{y}} and
                  Luk{\'{a}}s Burget and
                  Lori Lamel and
                  Odette Scharenborg and
                  Petr Motl{\'{\i}}cek},
  title        = {Rethinking End-to-End Evaluation of Decomposable Tasks: {A} Case Study
                  on Spoken Language Understanding},
  booktitle    = {22nd Annual Conference of the International Speech Communication Association,
                  Interspeech 2021, Brno, Czechia, August 30 - September 3, 2021},
  pages        = {1264--1268},
  publisher    = {{ISCA}},
  year         = {2021},
  url          = {https://doi.org/10.21437/Interspeech.2021-1537},
  doi          = {10.21437/INTERSPEECH.2021-1537},
  timestamp    = {Tue, 11 Jun 2024 16:45:43 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/AroraO0DM0B21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2104-14914,
  author       = {Siddhant Arora and
                  Vinayak Gupta and
                  Garima Gaur and
                  Srikanta Bedathur},
  title        = {{BERT} Meets Relational {DB:} Contextual Representations of Relational
                  Databases},
  journal      = {CoRR},
  volume       = {abs/2104.14914},
  year         = {2021},
  url          = {https://arxiv.org/abs/2104.14914},
  eprinttype   = {arXiv},
  eprint       = {2104.14914},
  timestamp    = {Tue, 04 May 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2104-14914.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2106-15065,
  author       = {Siddhant Arora and
                  Alissa Ostapenko and
                  Vijay Viswanathan and
                  Siddharth Dalmia and
                  Florian Metze and
                  Shinji Watanabe and
                  Alan W. Black},
  title        = {Rethinking End-to-End Evaluation of Decomposable Tasks: {A} Case Study
                  on Spoken Language Understanding},
  journal      = {CoRR},
  volume       = {abs/2106.15065},
  year         = {2021},
  url          = {https://arxiv.org/abs/2106.15065},
  eprinttype   = {arXiv},
  eprint       = {2106.15065},
  timestamp    = {Wed, 17 Nov 2021 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2106-15065.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2111-14706,
  author       = {Siddhant Arora and
                  Siddharth Dalmia and
                  Pavel Denisov and
                  Xuankai Chang and
                  Yushi Ueda and
                  Yifan Peng and
                  Yuekai Zhang and
                  Sujay Kumar and
                  Karthik Ganesan and
                  Brian Yan and
                  Ngoc Thang Vu and
                  Alan W. Black and
                  Shinji Watanabe},
  title        = {ESPnet-SLU: Advancing Spoken Language Understanding through ESPnet},
  journal      = {CoRR},
  volume       = {abs/2111.14706},
  year         = {2021},
  url          = {https://arxiv.org/abs/2111.14706},
  eprinttype   = {arXiv},
  eprint       = {2111.14706},
  timestamp    = {Fri, 27 Jun 2025 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2111-14706.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2112-09669,
  author       = {Siddhant Arora and
                  Danish Pruthi and
                  Norman M. Sadeh and
                  William W. Cohen and
                  Zachary C. Lipton and
                  Graham Neubig},
  title        = {Explain, Edit, and Understand: Rethinking User Study Design for Evaluating
                  Model Explanations},
  journal      = {CoRR},
  volume       = {abs/2112.09669},
  year         = {2021},
  url          = {https://arxiv.org/abs/2112.09669},
  eprinttype   = {arXiv},
  eprint       = {2112.09669},
  timestamp    = {Mon, 03 Jan 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2112-09669.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/akbc/AroraBRS20,
  author       = {Siddhant Arora and
                  Srikanta Bedathur and
                  Maya Ramanath and
                  Deepak Sharma},
  editor       = {Dipanjan Das and
                  Hannaneh Hajishirzi and
                  Andrew McCallum and
                  Sameer Singh},
  title        = {IterefinE: Iterative {KG} Refinement Embeddings using Symbolic Knowledge},
  booktitle    = {Conference on Automated Knowledge Base Construction, {AKBC} 2020,
                  Virtual, June 22-24, 2020},
  year         = {2020},
  url          = {https://doi.org/10.24432/C5NP46},
  doi          = {10.24432/C5NP46},
  timestamp    = {Tue, 12 Jan 2021 16:24:06 +0100},
  biburl       = {https://dblp.org/rec/conf/akbc/AroraBRS20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/wsdm/YatesAZYJL20,
  author       = {Andrew Yates and
                  Siddhant Arora and
                  Xinyu Zhang and
                  Wei Yang and
                  Kevin Martin Jose and
                  Jimmy Lin},
  editor       = {James Caverlee and
                  Xia (Ben) Hu and
                  Mounia Lalmas and
                  Wei Wang},
  title        = {Capreolus: {A} Toolkit for End-to-End Neural Ad Hoc Retrieval},
  booktitle    = {{WSDM} '20: The Thirteenth {ACM} International Conference on Web Search
                  and Data Mining, Houston, TX, USA, February 3-7, 2020},
  pages        = {861--864},
  publisher    = {{ACM}},
  year         = {2020},
  url          = {https://doi.org/10.1145/3336191.3371868},
  doi          = {10.1145/3336191.3371868},
  timestamp    = {Fri, 15 Dec 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/wsdm/YatesAZYJL20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2005-06437,
  author       = {Siddhant Arora and
                  Srikanta Bedathur},
  title        = {On Embeddings in Relational Databases},
  journal      = {CoRR},
  volume       = {abs/2005.06437},
  year         = {2020},
  url          = {https://arxiv.org/abs/2005.06437},
  eprinttype   = {arXiv},
  eprint       = {2005.06437},
  timestamp    = {Thu, 14 May 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2005-06437.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2006-04509,
  author       = {Siddhant Arora and
                  Srikanta Bedathur and
                  Maya Ramanath and
                  Deepak Sharma},
  title        = {IterefinE: Iterative {KG} Refinement Embeddings using Symbolic Knowledge},
  journal      = {CoRR},
  volume       = {abs/2006.04509},
  year         = {2020},
  url          = {https://arxiv.org/abs/2006.04509},
  eprinttype   = {arXiv},
  eprint       = {2006.04509},
  timestamp    = {Fri, 12 Jun 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2006-04509.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2007-12374,
  author       = {Siddhant Arora},
  title        = {A Survey on Graph Neural Networks for Knowledge Graph Completion},
  journal      = {CoRR},
  volume       = {abs/2007.12374},
  year         = {2020},
  url          = {https://arxiv.org/abs/2007.12374},
  eprinttype   = {arXiv},
  eprint       = {2007.12374},
  timestamp    = {Wed, 29 Jul 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2007-12374.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ecir/AroraY19,
  author       = {Siddhant Arora and
                  Andrew Yates},
  editor       = {J{\"{o}}ran Beel and
                  Lars Kotthoff},
  title        = {Investigating Retrieval Method Selection with Axiomatic Features},
  booktitle    = {Proceedings of the 1st Interdisciplinary Workshop on Algorithm Selection
                  and Meta-Learning in Information Retrieval co-located with the 41st
                  European Conference on Information Retrieval {(ECIR} 2019), Cologne,
                  Germany, April 14, 2019},
  series       = {{CEUR} Workshop Proceedings},
  pages        = {18--31},
  publisher    = {CEUR-WS.org},
  year         = {2019},
  url          = {https://ceur-ws.org/Vol-2360/paper4Axiomatic.pdf},
  timestamp    = {Fri, 10 Mar 2023 16:22:16 +0100},
  biburl       = {https://dblp.org/rec/conf/ecir/AroraY19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iui/KhoslaANSN19,
  author       = {Sopan Khosla and
                  Siddhant Arora and
                  Abhilash Nandy and
                  Ankita Saxena and
                  Anandhavelu Natarajan},
  editor       = {Christoph Trattner and
                  Denis Parra and
                  Nathalie Riche},
  title        = {Understanding Community Rivalry on Social Media: {A} Case Study of
                  Two Footballing Giants},
  booktitle    = {Joint Proceedings of the {ACM} {IUI} 2019 Workshops co-located with
                  the 24th {ACM} Conference on Intelligent User Interfaces {(ACM} {IUI}
                  2019), Los Angeles, USA, March 20, 2019},
  series       = {{CEUR} Workshop Proceedings},
  publisher    = {CEUR-WS.org},
  year         = {2019},
  url          = {https://ceur-ws.org/Vol-2327/IUI19WS-HUMANIZE-3.pdf},
  timestamp    = {Fri, 10 Mar 2023 16:23:10 +0100},
  biburl       = {https://dblp.org/rec/conf/iui/KhoslaANSN19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1904-05737,
  author       = {Siddhant Arora and
                  Andrew Yates},
  title        = {Investigating Retrieval Method Selection with Axiomatic Features},
  journal      = {CoRR},
  volume       = {abs/1904.05737},
  year         = {2019},
  url          = {http://arxiv.org/abs/1904.05737},
  eprinttype   = {arXiv},
  eprint       = {1904.05737},
  timestamp    = {Thu, 25 Apr 2019 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1904-05737.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/intellisys/SharmaAAAA18,
  author       = {Richa Sharma and
                  Tejas Arya and
                  Siddhant Arora and
                  Arti Arya and
                  Pooja Agarwal},
  editor       = {Kohei Arai and
                  Supriya Kapoor and
                  Rahul Bhatia},
  title        = {A Naive Deep Nets Based Approach for Authenticating Viral Textual
                  Content on Social Media},
  booktitle    = {Intelligent Systems and Applications - Proceedings of the 2018 Intelligent
                  Systems Conference, IntelliSys 2018, London, UK, September 6-7, 2018,
                  Volume 2},
  series       = {Advances in Intelligent Systems and Computing},
  pages        = {679--689},
  publisher    = {Springer},
  year         = {2018},
  url          = {https://doi.org/10.1007/978-3-030-01057-7\_52},
  doi          = {10.1007/978-3-030-01057-7\_52},
  timestamp    = {Tue, 18 Nov 2025 11:24:21 +0100},
  biburl       = {https://dblp.org/rec/conf/intellisys/SharmaAAAA18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}