{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T06:51:40Z","timestamp":1770274300262,"version":"3.49.0"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100004318","name":"Microsoft","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004318","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414464","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6898-6902","source":"Crossref","is-referenced-by-count":28,"title":["End-to-End Dereverberation, Beamforming, and Speech Recognition with Improved Numerical Stability and Advanced Frontend"],"prefix":"10.1109","author":[{"given":"Wangyou","family":"Zhang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,AI Institute, SpeechLab,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christoph","family":"Boeddeker","sequence":"additional","affiliation":[{"name":"Paderbom University,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomohiro","family":"Nakatani","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc","family":"Delcroix","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keisuke","family":"Kinoshita","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tsubasa","family":"Ochiai","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naoyuki","family":"Kamo","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Reinhold","family":"Haeb-Umbach","sequence":"additional","affiliation":[{"name":"Paderbom University,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,AI Institute, SpeechLab,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054029"},{"key":"ref38","first-page":"881","article-title":"A beamforming approach to permutation alignment for multichannel frequency-domain blind speech separation","author":"ikram","year":"2002","journal-title":"Proc IEEE ICASSP"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1002\/zamm.19290090206"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952242"},{"key":"ref30","first-page":"2632","article-title":"Multichannel end-to-end speech recognition","author":"ochiai","year":"2017","journal-title":"Proc ICML"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683294"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1974.1100466"},{"key":"ref35","article-title":"The matrix cookbook","volume":"3274","author":"petersen","year":"2012","journal-title":"Tech Rep Tech Univ Denmark"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2015.2513004"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1176"},{"key":"ref40","article-title":"BSS-EVAL Toolbox User Guide—Revision 2.0","author":"fevotte","year":"2005","journal-title":"IRISA Tech Rep 1706"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461893"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462507"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471664"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-552"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472778"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2764276"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953173"},{"key":"ref19","article-title":"An investigation of end-to-end multichannel speech recognition for reverberant and mismatch conditions","author":"subramanian","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/53.665"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"384","DOI":"10.21437\/Interspeech.2017-733","article-title":"Neural network-based spectrum estimation for online WPE dereverberation","author":"kinoshita","year":"2017","journal-title":"Proc ISCA Interspeech"},{"key":"ref3","article-title":"Wavesplit: End-to-end speech separation by speaker clustering","author":"zeghidour","year":"2020"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2020-1470","article-title":"Improved noisy student training for automatic speech recognition","author":"park","year":"2020"},{"key":"ref29","article-title":"NARA-WPE: A Python package for weighted prediction error dereverberation in Numpy and Tensorflow for online and offline processing","author":"drude","year":"2018","journal-title":"13 ITG Fachtagung Sprachkommunikation (ITG 2018)"},{"key":"ref5","article-title":"Single headed attention based sequence-to- sequence model for state-of-the-art results on switchboard- 300","author":"ttiske","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1700814"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907229"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404829"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2941148"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2052251"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2432"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003986"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.11.005"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.spl.2017.05.019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054393"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2911179"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414464.pdf?arnumber=9414464","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:18:25Z","timestamp":1659485905000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414464\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414464","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}