{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T16:01:44Z","timestamp":1783008104020,"version":"3.54.5"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,22]],"date-time":"2023-10-22T00:00:00Z","timestamp":1697932800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,22]],"date-time":"2023-10-22T00:00:00Z","timestamp":1697932800000},"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":[[2023,10,22]]},"DOI":"10.1109\/waspaa58266.2023.10248096","type":"proceedings-article","created":{"date-parts":[[2023,9,15]],"date-time":"2023-09-15T13:31:37Z","timestamp":1694784697000},"page":"1-5","source":"Crossref","is-referenced-by-count":8,"title":["Exploring the Integration of Speech Separation and Recognition with Self-Supervised Learning Representation"],"prefix":"10.1109","author":[{"given":"Yoshiki","family":"Masuyama","sequence":"first","affiliation":[{"name":"Tokyo Metropolitan University,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuankai","family":"Chang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wangyou","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samuele","family":"Cornell","sequence":"additional","affiliation":[{"name":"Università Politecnica Delle Marche,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhong-Qiu","family":"Wang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nobutaka","family":"Ono","sequence":"additional","affiliation":[{"name":"Tokyo Metropolitan University,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383556"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-234"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10727"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461639"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747554"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3145319"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3304482"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053327"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.832988"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-173"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953173"},{"key":"ref18","first-page":"2632","article-title":"Multichannel end-to-end speech recognition","volume-title":"Proc. ICML","author":"Ochiai"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682977"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003986"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632720"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2519"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462180"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-0999"},{"key":"ref25","first-page":"6903","article-title":"Streaming multi-speaker ASR with RNNT","volume-title":"Proc. ICASSP","author":"Sklyar"},{"key":"ref26","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NeurIPS","author":"Baevski"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.580"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10839"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023199"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688137"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471664"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2016-552"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2647702"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462081"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3209942"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414661"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747146"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053461"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2432"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414092"}],"event":{"name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","location":"New Paltz, NY, USA","start":{"date-parts":[[2023,10,22]]},"end":{"date-parts":[[2023,10,25]]}},"container-title":["2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10248019\/10248047\/10248096.pdf?arnumber=10248096","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T19:03:25Z","timestamp":1710356605000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10248096\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,22]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/waspaa58266.2023.10248096","relation":{},"subject":[],"published":{"date-parts":[[2023,10,22]]}}}