{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T08:10:39Z","timestamp":1764576639400,"version":"3.46.0"},"reference-count":49,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["EXC 2092 CASA \\u2013 390781972"],"award-info":[{"award-number":["EXC 2092 CASA \\u2013 390781972"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Speech & Language"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1016\/j.csl.2025.101869","type":"journal-article","created":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T15:19:59Z","timestamp":1756221599000},"page":"101869","update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Comparative study on noise-augmented training and its effect on adversarial robustness in ASR systems"],"prefix":"10.1016","volume":"96","author":[{"given":"Karla","family":"Pizzi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mat\u00edas","family":"Pizarro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Asja","family":"Fischer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.csl.2025.101869_b1","series-title":"2021 IEEE Symposium on Security and Privacy","first-page":"712","article-title":"Hear \u201cno evil\u201d, see \u201ckenansville\u201d: Efficient and transferable black-box attacks on speech recognition and voice identification systems","author":"Abdullah","year":"2021"},{"key":"10.1016\/j.csl.2025.101869_b2","series-title":"Proc. Interspeech 2015","first-page":"2849","article-title":"Robust speech recognition using DNN-HMM acoustic model combining noise-aware training with spectral subtraction","author":"Abe","year":"2015"},{"key":"10.1016\/j.csl.2025.101869_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.apacoust.2020.107631","article-title":"Improving deep speech denoising by noisy2noisy signal mapping","volume":"172","author":"Alamdari","year":"2021","journal-title":"Appl. Acoust."},{"year":"2018","series-title":"Did you hear that? adversarial examples against automatic speech recognition","author":"Alzantot","key":"10.1016\/j.csl.2025.101869_b4"},{"key":"10.1016\/j.csl.2025.101869_b5","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"vol. 34","author":"Baevski","year":"2020"},{"key":"10.1016\/j.csl.2025.101869_b6","series-title":"Proc. Interspeech 2019","first-page":"101","article-title":"Exploiting multi-channel speech presence probability in parametric multi-channel Wiener filter","author":"Bagheri","year":"2019"},{"key":"10.1016\/j.csl.2025.101869_b7","series-title":"2018 IEEE Security and Privacy Workshops","first-page":"1","article-title":"Audio adversarial examples: Targeted attacks on speech-to-text","author":"Carlini","year":"2018"},{"key":"10.1016\/j.csl.2025.101869_b8","series-title":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"4960","article-title":"Listen, attend and spell: A neural network for large vocabulary conversational speech recognition","author":"Chan","year":"2016"},{"key":"10.1016\/j.csl.2025.101869_b9","series-title":"Proceedings of the 28th International Conference on Neural Information Processing Systems - Volume 1","first-page":"577","article-title":"Attention-based models for speech recognition","author":"Chorowski","year":"2015"},{"issue":"2","key":"10.1016\/j.csl.2025.101869_b10","doi-asserted-by":"crossref","first-page":"475","DOI":"10.1007\/s10772-023-10033-0","article-title":"Noise robust automatic speech recognition: review and analysis","volume":"26","author":"Dua","year":"2023","journal-title":"Int. J. Speech Technol."},{"key":"10.1016\/j.csl.2025.101869_b11","article-title":"Robustness of classifiers: from adversarial to random noise","volume":"29","author":"Fawzi","year":"2016","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.csl.2025.101869_b12","series-title":"International Conference on Machine Learning","first-page":"2280","article-title":"Adversarial examples are a natural consequence of test error in noise","author":"Gilmer","year":"2019"},{"key":"10.1016\/j.csl.2025.101869_b13","series-title":"3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2015"},{"key":"10.1016\/j.csl.2025.101869_b14","series-title":"Proceedings of the 23rd International Conference on Machine Learning","first-page":"369","article-title":"Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks","author":"Graves","year":"2006"},{"year":"2014","series-title":"Deep speech: Scaling up end-to-end speech recognition","author":"Hannun","key":"10.1016\/j.csl.2025.101869_b15"},{"issue":"8","key":"10.1016\/j.csl.2025.101869_b16","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"10.1016\/j.csl.2025.101869_b17","doi-asserted-by":"crossref","unstructured":"Jakubovitz, D., Giryes, R., 2018. Improving DNN robustness to adversarial attacks using jacobian regularization. In: Proceedings of the European Conference on Computer Vision. ECCV, pp. 514\u2013529.","DOI":"10.1007\/978-3-030-01258-8_32"},{"key":"10.1016\/j.csl.2025.101869_b18","first-page":"3586","article-title":"Audio augmentation for speech recognition","volume":"vol. 2015","author":"Ko","year":"2015"},{"key":"10.1016\/j.csl.2025.101869_b19","series-title":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"5220","article-title":"A study on data augmentation of reverberant speech for robust speech recognition","author":"Ko","year":"2017"},{"key":"10.1016\/j.csl.2025.101869_b20","doi-asserted-by":"crossref","unstructured":"Laugros, A., Caplier, A., Ospici, M., 2019. Are adversarial robustness and common perturbation robustness independant attributes?. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops.","DOI":"10.1109\/ICCVW.2019.00134"},{"key":"10.1016\/j.csl.2025.101869_b21","article-title":"Certified adversarial robustness with additive noise","volume":"32","author":"Li","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.csl.2025.101869_b22","unstructured":"Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A., 2018. Towards deep learning models resistant to adversarial attacks. In: 6th International Conference on Learning Representations. ICLR."},{"issue":"6","key":"10.1016\/j.csl.2025.101869_b23","doi-asserted-by":"crossref","first-page":"1664","DOI":"10.1121\/1.383638","article-title":"Evaluation of a segmental SNR measure as an indicator of the quality of ADPCM coded speech","volume":"66","author":"Mermelstein","year":"1979","journal-title":"J. Acoust. Soc. Am."},{"year":"2023","series-title":"Assessing and Enhancing Adversarial Robustness in Context and Applications to Speech Security","author":"Olivier","key":"10.1016\/j.csl.2025.101869_b24"},{"key":"10.1016\/j.csl.2025.101869_b25","series-title":"Proc. Interspeech 2022","first-page":"4113","article-title":"Recent improvements of ASR models in the face of adversarial attacks","author":"Olivier","year":"2022"},{"key":"10.1016\/j.csl.2025.101869_b26","series-title":"Proc. Interspeech 2023","first-page":"4394","article-title":"There is more than one kind of robustness: Fooling whisper with adversarial examples","author":"Olivier","year":"2023"},{"key":"10.1016\/j.csl.2025.101869_b27","series-title":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"5206","article-title":"Librispeech: an ASR corpus based on public domain audio books","author":"Panayotov","year":"2015"},{"key":"10.1016\/j.csl.2025.101869_b28","series-title":"2016 IEEE Symposium on Security and Privacy","first-page":"582","article-title":"Distillation as a defense to adversarial perturbations against deep neural networks","author":"Papernot","year":"2016"},{"key":"10.1016\/j.csl.2025.101869_b29","series-title":"Proc. Interspeech 2019","first-page":"2613","article-title":"SpecAugment: A simple data augmentation method for automatic speech recognition","author":"Park","year":"2019"},{"key":"10.1016\/j.csl.2025.101869_b30","series-title":"ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"6879","article-title":"Specaugment on large scale datasets","author":"Park","year":"2020"},{"key":"10.1016\/j.csl.2025.101869_b31","series-title":"Proc. 2021 ISCA Symposium on Security and Privacy in Speech Communication","first-page":"37","article-title":"Robustifying automatic speech recognition by extracting slowly varying features","author":"Pizarro","year":"2021"},{"key":"10.1016\/j.csl.2025.101869_b32","series-title":"Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence","first-page":"2956","article-title":"Distriblock: Identifying adversarial audio samples by leveraging characteristics of the output distribution","volume":"vol. 244","author":"Pizarro","year":"2024"},{"key":"10.1016\/j.csl.2025.101869_b33","series-title":"4th Symposium on Security and Privacy in Speech Communication","first-page":"26","article-title":"Reassessing noise augmentation methods in the context of adversarial speech","author":"Pizzi","year":"2024"},{"key":"10.1016\/j.csl.2025.101869_b34","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1109\/TASLP.2023.3328283","article-title":"End-to-end speech recognition: A survey","volume":"32","author":"Prabhavalkar","year":"2024","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.csl.2025.101869_b35","series-title":"International Conference on Machine Learning","first-page":"5231","article-title":"Imperceptible, robust, and targeted adversarial examples for automatic speech recognition","author":"Qin","year":"2019"},{"year":"2021","series-title":"SpeechBrain: A general-purpose speech toolkit","author":"Ravanelli","key":"10.1016\/j.csl.2025.101869_b36"},{"key":"10.1016\/j.csl.2025.101869_b37","series-title":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"626","article-title":"SDR \u2013 half-baked or well done?","author":"Roux","year":"2019"},{"key":"10.1016\/j.csl.2025.101869_b38","doi-asserted-by":"crossref","DOI":"10.14722\/ndss.2019.23288","article-title":"Adversarial attacks against automatic speech recognition systems via psychoacoustic hiding","author":"Sch\u00f6nherr","year":"2019","journal-title":"Netw. Distrib. Syst. Secur. Symp. (NDSS)"},{"key":"10.1016\/j.csl.2025.101869_b39","series-title":"Proceedings of the 19th International Society for Music Information Retrieval Conference, ISMIR 2018, Paris, France, September 23-27, 2018","first-page":"334","article-title":"Wave-u-net: A multi-scale neural network for end-to-end audio source separation","author":"Stoller","year":"2018"},{"key":"10.1016\/j.csl.2025.101869_b40","series-title":"2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14-16, 2014, Conference Track Proceedings","article-title":"Intriguing properties of neural networks","author":"Szegedy","year":"2014"},{"key":"10.1016\/j.csl.2025.101869_b41","unstructured":"Tram\u00e8r, F., Kurakin, A., Papernot, N., Goodfellow, I., Boneh, D., McDaniel, P., 2018. Ensemble adversarial training: Attacks and defenses. In: 6th International Conference on Learning Representations. ICLR."},{"key":"10.1016\/j.csl.2025.101869_b42","article-title":"Attention is all you need","volume":"vol. 30","author":"Vaswani","year":"2017"},{"year":"2012","series-title":"Techniques for Noise Robustness in Automatic Speech Recognition","author":"Virtanen","key":"10.1016\/j.csl.2025.101869_b43"},{"key":"10.1016\/j.csl.2025.101869_b44","series-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations","first-page":"38","article-title":"Transformers: State-of-the-art natural language processing","author":"Wolf","year":"2020"},{"key":"10.1016\/j.csl.2025.101869_b45","series-title":"International Conference on Machine Learning","first-page":"5286","article-title":"Provable defenses against adversarial examples via the convex outer adversarial polytope","author":"Wong","year":"2018"},{"key":"10.1016\/j.csl.2025.101869_b46","doi-asserted-by":"crossref","unstructured":"Xie, C., Wu, Y., Maaten, L.v.d., Yuille, A.L., He, K., 2019. Feature denoising for improving adversarial robustness. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 501\u2013509.","DOI":"10.1109\/CVPR.2019.00059"},{"key":"10.1016\/j.csl.2025.101869_b47","doi-asserted-by":"crossref","DOI":"10.14722\/ndss.2018.23198","article-title":"Feature squeezing: Detecting adversarial examples in deep neural networks","author":"Xu","year":"2018","journal-title":"Netw. Distrib. Syst. Secur. Symp. (NDSS)"},{"year":"2021","series-title":"Adversarial attacks and defenses for speech recognition systems","author":"\u017belasko","key":"10.1016\/j.csl.2025.101869_b48"},{"key":"10.1016\/j.csl.2025.101869_b49","unstructured":"Zhang, H., Chen, H., Song, Z., Boning, D., Dhillon, I.S., Hsieh, C.J., 2019. The limitations of adversarial training and the blind-spot attack. In: 7th International Conference on Learning Representations. ICLR."}],"container-title":["Computer Speech & Language"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S0885230825000944?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S0885230825000944?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T08:09:14Z","timestamp":1764576554000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/linkinghub.elsevier.com\/retrieve\/pii\/S0885230825000944"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":49,"alternative-id":["S0885230825000944"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/j.csl.2025.101869","relation":{},"ISSN":["0885-2308"],"issn-type":[{"type":"print","value":"0885-2308"}],"subject":[],"published":{"date-parts":[[2026,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Comparative study on noise-augmented training and its effect on adversarial robustness in ASR systems","name":"articletitle","label":"Article Title"},{"value":"Computer Speech & Language","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/j.csl.2025.101869","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"101869"}}