{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:44:22Z","timestamp":1783439062740,"version":"3.54.6"},"reference-count":60,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746303","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"6837-6841","source":"Crossref","is-referenced-by-count":62,"title":["Investigating Self-Supervised Learning for Speech Enhancement and Separation"],"prefix":"10.1109","author":[{"given":"Zili","family":"Huang","sequence":"first","affiliation":[{"name":"Johns Hopkins University,Center for Language and Speech Processing and HLTCOE,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shu-wen","family":"Yang","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paola","family":"Garcia","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Center for Language and Speech Processing and HLTCOE,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanjeev","family":"Khudanpur","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Center for Language and Speech Processing and HLTCOE,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3090866"},{"key":"ref32","article-title":"Self-supervised pre-training reduces label permutation instability of speech separation","author":"huang","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414922"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref36","article-title":"Non-autoregressive predictive coding for learning speech representations from local dependencies","author":"liu","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1228"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1673"},{"key":"ref28","article-title":"Exploring wav2vec 2.0 on speaker verification and language identification","author":"fan","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054224"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-703"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3066303"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"ref21","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL-HLT (1)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref25","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref50","article-title":"Librimix: An open-source dataset for generalizable speech separation","author":"cosentino","year":"2020"},{"key":"ref51","first-page":"5206","article-title":"Librispeech: an asr corpus based on public domain audio books","author":"panayotov","year":"2015","journal-title":"ICASSP"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-236"},{"key":"ref58","first-page":"7669","article-title":"Libri-light: A benchmark for asr with limited or no supervision","author":"kahn","year":"2020","journal-title":"ICASSP"},{"key":"ref57","article-title":"Torchaudio: Building blocks for audio and speech processing","author":"yang","year":"2021"},{"key":"ref56","article-title":"python-pesq","author":"wang","year":"2019"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref54","article-title":"862.2: Wideband extension to recommendation p. 862 for the assessment of wideband telephone networks and speech codecs","year":"2007"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref40","first-page":"7414","article-title":"Unsupervised pretraining transfers well across languages","year":"2020","journal-title":"ICASSP"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952155"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1428","article-title":"SEGAN: Speech enhancement generative adversarial network","author":"pascual","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref16","first-page":"46","article-title":"Dual-path rnn: efficient long sequence modeling for time-domain single-channel speech separation","author":"luo","year":"2020","journal-title":"ICASSP"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2205"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3099291"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-9"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-1"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1007\/978-3-319-22482-4_11","article-title":"Speech enhancement with lstm recurrent neural networks and its application to noise-robust asr","author":"weninger","year":"2015","journal-title":"International Conference on Latent Variable Analysis and Signal Separation"},{"key":"ref5","article-title":"Ustc-nelslip system description for dihard-iii challenge","author":"wang","year":"2021"},{"key":"ref8","first-page":"2031","article-title":"Metricgan: Generative adversarial networks based black-box metric scores optimization for speech enhancement","author":"fu","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1121\/1.4799597"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462068"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-599"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709856"},{"key":"ref47","article-title":"Noisy speech database for training speech enhancement algorithms and tts models","author":"valentini-botinhao","year":"2017"},{"key":"ref42","first-page":"132","article-title":"Deep clustering for unsupervised learning of visual features","author":"caron","year":"2018","journal-title":"ECCV"},{"key":"ref41","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2020","journal-title":"ICLRE"},{"key":"ref44","article-title":"Wavlm: Large-scale self-supervised pre-training for full stack speech processing","author":"chen","year":"2021"},{"key":"ref43","article-title":"Unispeech-sat: Universal speech representation learning with speaker aware pre-training","author":"chen","year":"2021"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746303.pdf?arnumber=9746303","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T03:23:59Z","timestamp":1727061839000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746303\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746303","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}