{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T15:45:33Z","timestamp":1783611933414,"version":"3.55.0"},"reference-count":49,"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"}],"funder":[{"name":"JST Moonshot R&D","award":["JPMJMS2011"],"award-info":[{"award-number":["JPMJMS2011"]}]}],"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.2024.3407511","type":"journal-article","created":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T17:56:23Z","timestamp":1717091783000},"page":"3049-3060","source":"Crossref","is-referenced-by-count":23,"title":["Waveform-Domain Speech Enhancement Using Spectrogram Encoding for Robust Speech Recognition"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3373-2147","authenticated-orcid":false,"given":"Hao","family":"Shi","sequence":"first","affiliation":[{"name":"Graduate School of Informatics, Kyoto University, Kyoto, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masato","family":"Mimura","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Kyoto University, Kyoto, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2686-2296","authenticated-orcid":false,"given":"Tatsuya","family":"Kawahara","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Kyoto University, Kyoto, Japan"}],"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\/TASLP.2014.2304637"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22482-4_11"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054661"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2002.5745591"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/89.397090"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.5743702"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2013-130"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2409"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2913512"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682834"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2369251"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1405"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2968738"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2952"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2291240"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094718"},{"key":"ref20","article-title":"Hybrid spectrogram and waveform source separation","volume-title":"arXiv:2111.03600","author":"Dfossez","year":"2022"},{"key":"ref21","article-title":"Investigation of adapter for automatic speech recognition in noisy environment","author":"Shi","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747755"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3039600"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746314"},{"key":"ref25","first-page":"438","article-title":"Spectrograms fusion-based end-to-end robust automatic speech recognition","volume-title":"Proc. Asia-Pacific Signal Inf. Process. Assoc. Annu. Summit Conf.","author":"Shi","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1984.1172555"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2940662"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1938"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288816"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2998279"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7177943"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383615"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414878"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746108"},{"key":"ref39","first-page":"800","article-title":"End-to-end music-mixed speech recognition","volume-title":"Proc. Asia-Pacific Signal Inf. Process. Assoc. Annu. Summit Conf.","author":"Woo"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref42","article-title":"MUSAN: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1262"},{"key":"ref47","article-title":"A conformer based acoustic model for robust automatic speech recognition","author":"Yang","year":"2022"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-101"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10839"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10542371.pdf?arnumber=10542371","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T19:00:51Z","timestamp":1750100451000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10542371\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3407511","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}