{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:29:23Z","timestamp":1775230163785,"version":"3.50.1"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3426924","type":"journal-article","created":{"date-parts":[[2024,7,22]],"date-time":"2024-07-22T18:06:28Z","timestamp":1721671588000},"page":"3589-3602","source":"Crossref","is-referenced-by-count":10,"title":["Rethinking Processing Distortions: Disentangling the Impact of Speech Enhancement Errors on Speech Recognition Performance"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2519-2032","authenticated-orcid":false,"given":"Tsubasa","family":"Ochiai","sequence":"first","affiliation":[{"name":"NTT Corporation, Chiyoda-ku, Japan"}]},{"given":"Kazuma","family":"Iwamoto","sequence":"additional","affiliation":[{"name":"Doshisha Univer sity, Kyotanabe, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5175-7834","authenticated-orcid":false,"given":"Marc","family":"Delcroix","sequence":"additional","affiliation":[{"name":"NTT Corporation, Chiyoda-ku, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2608-1999","authenticated-orcid":false,"given":"Rintaro","family":"Ikeshita","sequence":"additional","affiliation":[{"name":"NTT Corporation, Chiyoda-ku, Japan"}]},{"given":"Hiroshi","family":"Sato","sequence":"additional","affiliation":[{"name":"NTT Corporation, Chiyoda-ku, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4363-4305","authenticated-orcid":false,"given":"Shoko","family":"Araki","sequence":"additional","affiliation":[{"name":"NTT Corporation, Chiyoda-ku, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4738-5385","authenticated-orcid":false,"given":"Shigeru","family":"Katagiri","sequence":"additional","affiliation":[{"name":"Doshisha Univer sity, Kyotanabe, Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref2","volume-title":"Automatic Speech Recognition","author":"Yu","year":"2016"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref5","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3018668"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404837"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1768"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472671"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471664"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461669"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2018-8"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683634"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2023.3240008"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404828"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1262"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1270"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682460"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10839"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.11.005"},{"key":"ref26","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Radford","year":"2023"},{"key":"ref27","first-page":"800","article-title":"End-to-end music-mixed speech recognition","volume-title":"Proc. IEEE Asia-Pacific Signal Inf. Process. Assoc. Annu. Summit Conf. (APSIPA)","author":"Woo","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2519"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2528171"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/89.279283"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1983.1171927"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632756"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3126931"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3290428"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-318"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747584"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1193"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2253"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746347"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414661"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659758"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-302"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref45","first-page":"1","article-title":"Spontaneous speech corpus of Japanese","volume-title":"Proc. LREC","volume":"6","author":"Maekawa","year":"2000"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1121\/1.4806631"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1121\/1.382599"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09905-3"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.10.005"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053266"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8683855"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref53","first-page":"1310","article-title":"On the difficulty of training recurrent neural networks","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Pascanu","year":"2013"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1673"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447750"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2016-595"},{"key":"ref58","article-title":"The Kaldi speech recognition toolkit","volume-title":"Proc. IEEE Autom. Speech Recognit. Understanding Workshop (ASRU)","author":"Povey","year":"2011"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10606400.pdf?arnumber=10606400","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,30]],"date-time":"2024-07-30T05:01:19Z","timestamp":1722315679000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10606400\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3426924","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}