{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:31:05Z","timestamp":1776889865979,"version":"3.51.2"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389724","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T13:38:40Z","timestamp":1705671520000},"page":"1-6","source":"Crossref","is-referenced-by-count":8,"title":["A Single Speech Enhancement Model Unifying Dereverberation, Denoising, Speaker Counting, Separation, And Extraction"],"prefix":"10.1109","author":[{"given":"Kohei","family":"Saijo","sequence":"first","affiliation":[{"name":"Waseda University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wangyou","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhong-Qiu","family":"Wang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tetsunori","family":"Kobayashi","sequence":"additional","affiliation":[{"name":"Waseda University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tetsuji","family":"Ogawa","sequence":"additional","affiliation":[{"name":"Waseda University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3018668"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10094992"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2922820"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1101"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2023.3240008"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683448"},{"key":"ref11","first-page":"7164","article-title":"Voice separation with an unknown number of multiple speakers","volume-title":"Proc. ICML","author":"Nachmani"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414205"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2795749"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-0034"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414774"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462646"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1550"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2519"},{"key":"ref20","first-page":"3735","article-title":"Sequence to multi-sequence learning via conditional chain mapping for mixture signals","volume":"33","author":"Shi","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268572"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3162080"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937253"},{"key":"ref24","article-title":"Universal speech enhancement with score-based diffusion","author":"Serr\u00e0","year":"2022","journal-title":"arXiv preprint arXiv:2206.03065"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2205"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref28","volume-title":"CSR-I (WSJ0) Complete LDC93S6A","author":"Garofolo","year":"1993"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461310"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701894"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383615"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref35","article-title":"Adam: A method for stochastic optimization","volume-title":"ICLR","author":"Diederik"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747473"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref39","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022","journal-title":"arXiv preprint arXiv:2212.04356"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Taipei, Taiwan","start":{"date-parts":[[2023,12,16]]},"end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389724.pdf?arnumber=10389724","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T11:36:17Z","timestamp":1706009777000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389724\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389724","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}