{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:22:44Z","timestamp":1776885764243,"version":"3.51.2"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100018696","name":"Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018696","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434718","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-8","source":"Crossref","is-referenced-by-count":3,"title":["Improving Speech Enhancement with Multi-Metric Supervision from Learned Quality Assessment"],"prefix":"10.1109","author":[{"given":"Wei","family":"Wang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,China"}]},{"given":"Wangyou","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,China"}]},{"given":"Chenda","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,China"}]},{"given":"Jaitong","family":"Shi","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}]},{"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1201\/b14529"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8683855"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-318"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2946789"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889088"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389685"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632720"},{"key":"ref8","article-title":"Less is more: Data curation matters in scaling speech enhancement","author":"Li","year":"2025","journal-title":"arXiv preprint arXiv:2506.23859"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-1668"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1250\/ast.e24.12"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3069302"},{"key":"ref12","article-title":"Versa: A versatile evaluation toolkit for speech, audio, and music","author":"Shi","year":"2024","journal-title":"arXiv e-prints"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-1246"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1109\/ASRU65441.2025.11434623","article-title":"Meta audiobox aesthetics: Unified automatic quality assessment for speech, music, and sound","author":"Tjandra","year":"2025"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746108"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832315"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-970"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389763"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832295"},{"key":"ref21","article-title":"Urgent-pk: Perceptually-aligned ranking model designed for speech enhancement competition","author":"Wang","year":"2025","journal-title":"arXiv preprint arXiv:2506.23874"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2025.3526550"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-1960"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"issue":"6","key":"ref25","first-page":"366","article-title":"Perceptual objective listening quality assessment (POLQA), the third generation ITU-T standard for end-to-end speech quality measurement part I-temporal alignment","volume":"61","author":"Beerends","year":"2013","journal-title":"AES Journal"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1239"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-1363"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888007"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-299"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3353"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1194"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1508"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.30420\/456164052"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1345"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-1246"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162849"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-1977"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/chime.2023-2"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746395"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Blizzard.2019-1"},{"key":"ref45","article-title":"Mos-bench: Benchmarking generalization abilities of subjective speech quality assessment models","author":"Huang","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3038"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.11.005"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref51","doi-asserted-by":"crossref","first-page":"1893","DOI":"10.1109\/TASLP.2023.3271145","article-title":"Music source separation with band-split rnn","volume":"31","author":"Luo","year":"2022","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.06083"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3416965"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434718.pdf?arnumber=11434718","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:58:42Z","timestamp":1775192322000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434718\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434718","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}