{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T13:08:39Z","timestamp":1782824919898,"version":"3.54.5"},"reference-count":38,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414127","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"5739-5743","source":"Crossref","is-referenced-by-count":9,"title":["Dual-Path Modeling for Long Recording Speech Separation in Meetings"],"prefix":"10.1109","author":[{"given":"Chenda","family":"Li","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, SpeechLab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuo","family":"Chen","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Luo","sequence":"additional","affiliation":[{"name":"Columbia University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cong","family":"Han","sequence":"additional","affiliation":[{"name":"Columbia University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keisuke","family":"Kinoshita","sequence":"additional","affiliation":[{"name":"NTT Corporation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marc","family":"Delcroix","sequence":"additional","affiliation":[{"name":"NTT Corporation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, SpeechLab"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref38","first-page":"785","article-title":"ESPNet-SE: End-to-end speech enhancement and separation toolkit designed for ASR integration","author":"li","year":"2021","journal-title":"Proc IEEE SLT"},{"key":"ref33","first-page":"630","article-title":"Identity mappings in deep residual networks","author":"he","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref32","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2205"},{"key":"ref37","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1121\/1.382599"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003884"},{"key":"ref13","article-title":"Wavesplit: End-to-end speech separation by speaker clustering","author":"zeghidour","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054177"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"2456","DOI":"10.21437\/Interspeech.2017-305","article-title":"Recognizing multi-talker speech with permutation invariant training","author":"yu","year":"2017","journal-title":"Proc ISCA Interspeech"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461893"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003986"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2988423"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2519"},{"key":"ref28","first-page":"865","article-title":"Dual-path RNN for long recording speech separation","author":"li","year":"2021","journal-title":"Proc IEEE SLT"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2388"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2795749"},{"key":"ref29","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952155"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462507"},{"key":"ref7","first-page":"61","article-title":"Deep clustering and conventional networks for music separation: Stronger together","author":"luo","year":"2017","journal-title":"Proc IEEE ICASSP"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1176"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref20","article-title":"Investigation of end-to-end speaker-attributed asr for continuous multi-talker recordings","author":"kanda","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003827"},{"key":"ref21","article-title":"Analysis of overlaps in meetings by dialog factors, hot spots, speakers, and collection site: Insights for automatic speech recognition","author":"\u00e7etin","year":"2006","journal-title":"Ninth International Conference on Spoken Language Processing"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1101"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053426"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462661"}],"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\/09414127.pdf?arnumber=9414127","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:19:45Z","timestamp":1659485985000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414127\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414127","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}