{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:03:55Z","timestamp":1750309435811,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":18,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,21]],"date-time":"2024-06-21T00:00:00Z","timestamp":1718928000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,21]]},"DOI":"10.1145\/3690407.3690478","type":"proceedings-article","created":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T18:55:28Z","timestamp":1729796128000},"page":"420-424","update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Speech Recognition of Noisy Tibetan Based on Parallel Branch Structure"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0003-1477-4958","authenticated-orcid":false,"given":"Zhenye","family":"Gan","sequence":"first","affiliation":[{"name":"College of Physics and Electronic Engineering, Northwest Normal University, Lanzhou, Gansu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0009-0007-3152-3524","authenticated-orcid":false,"given":"Feilong","family":"Zhai","sequence":"additional","affiliation":[{"name":"College of Physics and Electronic Engineering, Northwest Normal University, Lanzhou, Gansu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,24]]},"reference":[{"key":"e_1_3_3_1_1_2","first-page":"4960","article-title":"Listen, attend and spell: A neural network for large vocabulary conversational speech recognition[C]\/\/2016 IEEE international conference on acoustics, speech and signal processing (ICASSP)","volume":"2016","author":"Chan W","unstructured":"Chan W, Jaitly N, Le Q, et al. Listen, attend and spell: A neural network for large vocabulary conversational speech recognition[C]\/\/2016 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, 2016: 4960-4964.","journal-title":"IEEE"},{"key":"e_1_3_3_1_2_2","volume-title":"Contextnet: Improving convolutional neural networks for automatic speech recognition with global context[J]. arxiv preprint arxiv","author":"Han W","year":"2005","unstructured":"Han W, Zhang Z, Zhang Y, et al. Contextnet: Improving convolutional neural networks for automatic speech recognition with global context[J]. arxiv preprint arxiv: 2005.03191, 2020."},{"key":"e_1_3_3_1_3_2","first-page":"7829","article-title":"Transformer transducer: A streamable speech recognition model with transformer encoders and rnn-t loss[C]\/\/ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"2020","author":"Zhang Q","unstructured":"Zhang Q, Lu H, Sak H, et al. Transformer transducer: A streamable speech recognition model with transformer encoders and rnn-t loss[C]\/\/ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2020: 7829-7833.","journal-title":"IEEE"},{"key":"e_1_3_3_1_4_2","volume-title":"Conformer: Convolution-augmented transformer for speech recognition[J]. arxiv preprint arxiv","author":"Gulati A","year":"2005","unstructured":"Gulati A, Qin J, Chiu C C, et al. Conformer: Convolution-augmented transformer for speech recognition[J]. arxiv preprint arxiv: 2005.08100, 2020."},{"volume-title":"PMLR","author":"Peng Y","key":"e_1_3_3_1_5_2","unstructured":"Peng Y, Dalmia S, Lane I, et al. Branchformer: Parallel mlp-attention architectures to capture local and global context for speech recognition and understanding[C]\/\/International Conference on Machine Learning. PMLR, 2022: 17627-17643"},{"key":"e_1_3_3_1_6_2","volume-title":"E-branchformer: Branchformer with enhanced merging for speech recognition[C]\/\/2022 IEEE Spoken Language Technology Workshop (SLT)","author":"Kim K","year":"2023","unstructured":"Kim K, Wu F, Peng Y, et al. E-branchformer: Branchformer with enhanced merging for speech recognition[C]\/\/2022 IEEE Spoken Language Technology Workshop (SLT). IEEE, 2023: 84-91."},{"key":"e_1_3_3_1_7_2","volume-title":"Serra J. SEGAN: Speech enhancement generative adversarial network[J]. arxiv preprint arxiv: 1703.09452","author":"Pascual S","year":"2017","unstructured":"Pascual S, Bonafonte A, Serra J. SEGAN: Speech enhancement generative adversarial network[J]. arxiv preprint arxiv: 1703.09452, 2017."},{"key":"e_1_3_3_1_8_2","volume-title":"A conditional generative model for speech enhancement[J]. Circuits, Systems, and Signal Processing","author":"Li Z X","year":"2018","unstructured":"Li Z X, Dai L R, Song Y, et al. A conditional generative model for speech enhancement[J]. Circuits, Systems, and Signal Processing, 2018, 37: 5005-5022"},{"key":"e_1_3_3_1_9_2","volume-title":"On loss functions and recurrency training for GAN-based speech enhancement systems[J]. arxiv preprint arxiv","author":"Zhang Z","year":"2007","unstructured":"Zhang Z, Deng C, Shen Y, et al. On loss functions and recurrency training for GAN-based speech enhancement systems[J]. arxiv preprint arxiv: 2007.14974, 2020."},{"volume-title":"PMLR","author":"Fu S W","key":"e_1_3_3_1_10_2","unstructured":"Fu S W, Liao C F, Tsao Y, et al. Metricgan: Generative adversarial networks based black-box metric scores optimization for speech enhancement[C]\/\/International Conference on Machine Learning. PMLR, 2019: 2031-2041."},{"key":"e_1_3_3_1_11_2","first-page":"161","article-title":"DF-Conformer: Integrated architecture of Conv-TasNet and Conformer using linear complexity self-attention for speech enhancement[C]\/\/2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","volume":"2021","author":"Koizumi Y","unstructured":"Koizumi Y, Karita S, Wisdom S, et al. DF-Conformer: Integrated architecture of Conv-TasNet and Conformer using linear complexity self-attention for speech enhancement[C]\/\/2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA). IEEE, 2021: 161-165.","journal-title":"IEEE"},{"key":"e_1_3_3_1_12_2","volume-title":"Yang B. Cmgan: Conformer-based metric gan for speech enhancement[J]. arxiv preprint arxiv: 2203.15149","author":"Cao R","year":"2022","unstructured":"Cao R, Abdulatif S, Yang B. Cmgan: Conformer-based metric gan for speech enhancement[J]. arxiv preprint arxiv: 2203.15149, 2022."},{"key":"e_1_3_3_1_13_2","first-page":"7092","article-title":"Ideal ratio mask estimation using deep neural networks for robust speech recognition[C]\/\/2013 IEEE international conference on acoustics, speech and signal processing","volume":"2013","author":"Narayanan A","unstructured":"Narayanan A, Wang D L. Ideal ratio mask estimation using deep neural networks for robust speech recognition[C]\/\/2013 IEEE international conference on acoustics, speech and signal processing. IEEE, 2013: 7092-7096.","journal-title":"IEEE"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Wang J Yang Y Mao J et al. Cnn-rnn: A unified framework for multi-label image classification[C]\/\/Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 2285-2294.","DOI":"10.1109\/CVPR.2016.251"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1515\/jisys-2018-0372"},{"key":"e_1_3_3_1_16_2","volume-title":"Lite transformer with long-short range attention. arxiv 2020[J]. arxiv preprint arxiv","author":"Wu Z","year":"2004","unstructured":"Wu Z, Liu Z, Lin J, et al. Lite transformer with long-short range attention. arxiv 2020[J]. arxiv preprint arxiv: 2004.11886."},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICICSP50920.2020.9232119"},{"key":"e_1_3_3_1_18_2","first-page":"219","volume-title":"Power and Computer Engineering (EPCE)","author":"Zhenye Gan","year":"2023","unstructured":"Zhenye Gan, Zhenxing Kong, and Min Zhang. (2023). Research on tibetan speech recognition based on cnn-dfsmn-ctc. In 2023 2nd AsiaConference on Electrical, Power and Computer Engineering (EPCE), pages 215\u2013219. IEEE."}],"event":{"name":"CAIBDA 2024: 2024 4th International Conference on Artificial Intelligence, Big Data and Algorithms","acronym":"CAIBDA 2024","location":"Zhengzhou China"},"container-title":["Proceedings of the 2024 4th International Conference on Artificial Intelligence, Big Data and Algorithms"],"original-title":[],"link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/dl.acm.org\/doi\/10.1145\/3690407.3690478","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/dl.acm.org\/doi\/pdf\/10.1145\/3690407.3690478","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:09:37Z","timestamp":1750295377000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/dl.acm.org\/doi\/10.1145\/3690407.3690478"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,21]]},"references-count":18,"alternative-id":["10.1145\/3690407.3690478","10.1145\/3690407"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1145\/3690407.3690478","relation":{},"subject":[],"published":{"date-parts":[[2024,6,21]]},"assertion":[{"value":"2024-10-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}