{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:12:28Z","timestamp":1776885148898,"version":"3.51.2"},"reference-count":49,"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\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","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\/asru65441.2025.11434638","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":4,"title":["Less is More: Data Curation Matters in Scaling Speech Enhancement"],"prefix":"10.1109","author":[{"given":"Chenda","family":"Li","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,China"}]},{"given":"Wangyou","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,China"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,China"}]},{"given":"Robin","family":"Scheibler","sequence":"additional","affiliation":[{"name":"Google DeepMind,Japan"}]},{"given":"Kohei","family":"Saijo","sequence":"additional","affiliation":[{"name":"Waseda University,Japan"}]},{"given":"Samuele","family":"Cornell","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}]},{"given":"Yihui","family":"Fu","sequence":"additional","affiliation":[{"name":"Technische Universität,Braunschweig,Germany"}]},{"given":"Marvin","family":"Sach","sequence":"additional","affiliation":[{"name":"Technische Universität,Braunschweig,Germany"}]},{"given":"Zhaoheng","family":"Ni","sequence":"additional","affiliation":[{"name":"Meta,USA"}]},{"given":"Anurag","family":"Kumar","sequence":"additional","affiliation":[{"name":"Google DeepMind,Japan"}]},{"given":"Tim","family":"Fingscheidt","sequence":"additional","affiliation":[{"name":"Technische Universität,Braunschweig,Germany"}]},{"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\/9781420015836"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2024.3378602"},{"key":"ref7","article-title":"Improving speech enhancement with multi-metric supervision from learned quality assessment","author":"Wang","year":"2025","journal-title":"arXiv preprint arXiv:2506.12260"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-1668"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746901"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832147"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285241"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888274"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-159"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1266"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3449221"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1239"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2025-1363"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1108\/RR-08-2013-0197"},{"key":"ref19","first-page":"4218","article-title":"Common Voice: A Massively-Multilingual Speech Corpus","volume-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference","author":"Ardila"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709856"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-1246"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-478"},{"key":"ref23","article-title":"Self-Supervised Speech Quality Estimation and Enhancement Using Only Clean Speech","volume-title":"The Twelfth International Conference on Learning Representations","author":"Fu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888007"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414878"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-153"},{"key":"ref27","article-title":"BSS_EVAL Toolbox User Guide - Revision 2.0","author":"F\u00e9votte","year":"2005"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref31","article-title":"CSR-I (WSJ0) Complete","author":"Garofolo","year":"2007"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-299"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2025.3526550"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096680"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094992"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162849"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096020"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3271145"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448061"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747554"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383615"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747146"},{"key":"ref47","article-title":"Flow Matching for Generative Modeling","volume-title":"The Eleventh International Conference on Learning Representations","author":"Lipman"},{"key":"ref48","article-title":"Score-Based Generative Modeling through Stochastic Differential Equations","volume-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event","author":"Song"},{"key":"ref49","article-title":"Scale this, not that: Investigating key dataset attributes for efficient speech enhancement scaling","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv:2412.14890"}],"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\/11434638.pdf?arnumber=11434638","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:57:36Z","timestamp":1775192256000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434638\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434638","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}