{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:24:03Z","timestamp":1775229843518,"version":"3.50.1"},"reference-count":40,"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\/icassp43922.2022.9747146","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"9201-9205","source":"Crossref","is-referenced-by-count":22,"title":["Towards Low-Distortion Multi-Channel Speech Enhancement: The ESPNET-Se Submission to the L3DAS22 Challenge"],"prefix":"10.1109","author":[{"given":"Yen-Ju","family":"Lu","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,USA"}]},{"given":"Samuele","family":"Cornell","sequence":"additional","affiliation":[{"name":"Università Politecnica delle Marche,Italy"}]},{"given":"Xuankai","family":"Chang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}]},{"given":"Wangyou","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai"}]},{"given":"Chenda","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai"}]},{"given":"Zhaoheng","family":"Ni","sequence":"additional","affiliation":[{"name":"Meta AI,USA"}]},{"given":"Zhong-Qiu","family":"Wang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2014.80"},{"key":"ref38","article-title":"Hybrid spectrogram and waveform source separation","author":"d\u00e9fossez","year":"2021","journal-title":"Proc ISMIR"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3116502"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3145319"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053610"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054177"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref35","article-title":"Learning filterbanks for end-to-end acoustic beamforming","author":"cornell","year":"2021"},{"key":"ref34","article-title":"Demucs: Deep extractor for music sources with extra unlabeled data remixed","author":"d\u00e9fossez","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053989"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2792745.2792775"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2976193"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3083405"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-733"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471664"},{"key":"ref15","article-title":"Sdr– half-baked or well done?","author":"le roux","year":"2019","journal-title":"Proc ICASSP"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2022-318","article-title":"How bad are artifacts?: Analyzing the impact of speech enhancement errors on ASR","author":"iwamoto","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632720"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462622"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461669"},{"key":"ref27","article-title":"FSD50K: An open dataset of human-labeled sound events","author":"fonseca","year":"2021","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404829"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2764276"},{"key":"ref29","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-552"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003849"},{"key":"ref7","article-title":"Sequential multiframe neural beamforming for speech separation and enhancement","author":"wang","year":"2021","journal-title":"Proc SLT"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP52302.2021.9596418"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/9781119279860"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383615"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129363"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746872"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2911179"},{"key":"ref23","article-title":"Leveraging low-distortion target estimates for improved speech enhancement","author":"wang","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129335"}],"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\/09747146.pdf?arnumber=9747146","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T03:20:57Z","timestamp":1727061657000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747146\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747146","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}