{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:16:55Z","timestamp":1787012215880,"version":"build-2736575974"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10887859","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Speech Enhancement with MAP-based Training for Robust ASR"],"prefix":"10.1109","author":[{"given":"You-Jin","family":"Li","sequence":"first","affiliation":[{"name":"National Taiwan University,Taipei,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rong","family":"Chao","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taipei,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Borching","family":"Su","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taipei,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Tsao","sequence":"additional","affiliation":[{"name":"Academia Sinica,Taipei,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1201\/9781420015836"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2180896"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/9781119060970"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1121\/1.5055562"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2016.2613960"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2887337"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404828"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2014-148"},{"key":"ref9","article-title":"Multichannel endto-end speech recognition","volume-title":"Proc. ICML","author":"Ochiai"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383624"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746347"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10839"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-1620"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389793"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-130"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1900"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3050386"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8281993"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054536"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/ssw.2016-24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22482-4_11"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2409"},{"key":"ref25","article-title":"MetricGAN: Generative adversarial networks based black-box metric scores optimization for speech enhancement","volume-title":"Proc. ICML","author":"Fu"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3393718"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1441"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832332"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687924"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389733"},{"key":"ref31","article-title":"D4AM: A general denoising framework for downstream acoustic models","volume-title":"Proc. ICLR","author":"Lee"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-318"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389685"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3275033"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO63174.2024.10715447"},{"key":"ref36","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-49127-9_43"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1155\/ASP.2005.1110"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2015.10.003"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-599"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-456"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-159"},{"key":"ref43","article-title":"Performance analysis of the aurora large vocabulary baseline system","volume-title":"Proc. EUSIPCO","author":"Parihar"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(01)00041-3"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/asru.2003.1318504"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10887859.pdf?arnumber=10887859","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:26Z","timestamp":1774416266000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887859\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887859","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}