{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T14:53:13Z","timestamp":1779375193449,"version":"3.53.1"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389648","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-9","source":"Crossref","is-referenced-by-count":25,"title":["TorchAudio 2.1: Advancing Speech Recognition, Self-Supervised Learning, and Audio Processing Components for Pytorch"],"prefix":"10.1109","author":[{"given":"Jeff","family":"Hwang","sequence":"first","affiliation":[{"name":"Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Moto","family":"Hira","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Caroline","family":"Chen","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoheng","family":"Ni","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangzhi","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Cambridge"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pingchuan","family":"Ma","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruizhe","family":"Huang","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vineel","family":"Pratap","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuekai","family":"Zhang","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anurag","family":"Kumar","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chin-Yun","family":"Yu","sequence":"additional","affiliation":[{"name":"Queen Mary University of London"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuang","family":"Zhu","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunxi","family":"Liu","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jacob","family":"Kahn","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mirco","family":"Ravanelli","sequence":"additional","affiliation":[{"name":"Concordia University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Sun","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yangyang","family":"Shi","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yumeng","family":"Tao","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","author":"Abadi","journal-title":"2015, Software available from tensorflow.org"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747236"},{"key":"ref4","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-329"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414560"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2649-2"},{"key":"ref13","article-title":"Lhotse: a speech data representation library for the modern deep learning ecosystem","volume":"abs\/2110.12561","author":"\u017belasko","year":"2021","journal-title":"ArXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref15","article-title":"Speechbrain: A general-purpose speech toolkit","author":"Ravanelli","year":"2021","journal-title":"arXiv preprint arXiv:2106.04624"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref17","article-title":"Nemo: a toolkit for building ai applications using neural modules","author":"Kuchaiev","year":"2019","journal-title":"arXiv preprint arXiv:1909.09577"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1176"},{"key":"ref20","first-page":"10557","article-title":"Flashlight: Enabling innovation in tools for machine learning","author":"Kahn","year":"2022","journal-title":"ICML"},{"key":"ref21","first-page":"187","article-title":"Kenlm: Faster and smaller language model queries","volume-title":"Proceedings of the Sixth Workshop on Statistical Machine Translation","author":"Heafield"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414858"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10920"},{"key":"ref24","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","author":"Shi","year":"2022","journal-title":"ICLR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096889"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-487"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60276-5_27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8683535"},{"key":"ref29","article-title":"Scaling speech technology to 1,000+ languages","author":"Pratap","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2019.2918706"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471702"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2016-552"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413594"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096680"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1223"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2680"},{"key":"ref37","article-title":"MUSAN: A Music, Speech, and Noise Corpus","author":"Snyder","year":"2015","journal-title":"arXiv:1510.08484v1"},{"key":"ref38","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref39","article-title":"LRS3-TED: a large-scale dataset for visual speech recognition","author":"Afouras","year":"2018","journal-title":"arXiv preprint arXiv:1809.00496"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref42","article-title":"Jointly learning visual and auditory speech representations from raw data","author":"Haliassos","year":"2023","journal-title":"ICLR"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-99"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746872"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414661"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747146"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003849"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2537"},{"key":"ref49","article-title":"Hybrid spectrogram and waveform source separation","author":"D\u00e9fossez","year":"2021","journal-title":"arXiv preprint arXiv:2111.03600"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Taipei, Taiwan","start":{"date-parts":[[2023,12,16]]},"end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389648.pdf?arnumber=10389648","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:33:36Z","timestamp":1706027616000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389648\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389648","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}