{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:19:29Z","timestamp":1776889169379,"version":"3.51.2"},"reference-count":39,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,19]]},"DOI":"10.1109\/slt48900.2021.9383522","type":"proceedings-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T20:46:54Z","timestamp":1616705214000},"page":"905-911","source":"Crossref","is-referenced-by-count":35,"title":["Sequential Multi-Frame Neural Beamforming for Speech Separation and Enhancement"],"prefix":"10.1109","author":[{"given":"Zhong-Qiu","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hakan","family":"Erdogan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Scott","family":"Wisdom","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin","family":"Wilson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Desh","family":"Raj","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John R.","family":"Hershey","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"crossref","DOI":"10.21437\/CHiME.2020-1","article-title":"CHiME-6 challenge: Tackling multispeaker speech recognition for unsegmented recordings","author":"watanabe","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2917582"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2015.7336912"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053426"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref37","article-title":"Integration of speech separation, diarization, and recognition for multi-speaker meetings: System description, comparison, and analysis","author":"raj","year":"2020","journal-title":"2020 IEEE Workshop on Spoken Language Technology (SLT)"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2277"},{"key":"ref35","article-title":"SDR– half-baked or well done?","author":"le roux","year":"2019","journal-title":"Proc ICASSP"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1145\/3197517.3201357","article-title":"Looking to listen at the cocktail party: A speaker-independent audio-visual model for speech separation","author":"ephrat","year":"2018","journal-title":"ACM Transactions on Graphics"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639593"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462661"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1101"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937253"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952161"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682783"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683231"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2911179"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461669"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2405476"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.10.005"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683092"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682274"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461639"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462081"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-552"},{"key":"ref9","article-title":"Combining spectral and spatial features for deep learning based blind speaker separation","volume":"27","author":"wang","year":"2018","journal-title":"IEEE\/ACM TASLP"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471664"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404829"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/EEEI.2010.5662190"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2025790"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2050716"},{"key":"ref23","article-title":"High-quality, low-delay music coding in the Opus codec","author":"valin","year":"2016","journal-title":"Proc of AES Convention"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2907015"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472671"}],"event":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","location":"Shenzhen, China","start":{"date-parts":[[2021,1,19]]},"end":{"date-parts":[[2021,1,22]]}},"container-title":["2021 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9383468\/9383452\/09383522.pdf?arnumber=9383522","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,22]],"date-time":"2022-12-22T13:16:30Z","timestamp":1671714990000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9383522\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,19]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/slt48900.2021.9383522","relation":{},"subject":[],"published":{"date-parts":[[2021,1,19]]}}}