{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:51:26Z","timestamp":1764399086931,"version":"3.46.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249181","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"537-542","source":"Crossref","is-referenced-by-count":0,"title":["End-to-End Integration of Speech Emotion Recognition and Voice Activity Detection with a Self-Supervised Model for Noise Robustness"],"prefix":"10.1109","author":[{"given":"Natsuo","family":"Yamashita","sequence":"first","affiliation":[{"name":"Hitachi, Ltd.,Research &#x0026; Development Group,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masaaki","family":"Yamamoto","sequence":"additional","affiliation":[{"name":"Hitachi, Ltd.,Research &#x0026; Development Group,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yohei","family":"Kawaguchi","sequence":"additional","affiliation":[{"name":"Hitachi, Ltd.,Research &#x0026; Development Group,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.04.003"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0706743719828977"},{"key":"ref3","first-page":"22","article-title":"Emotion in speech: Recognition and application to call centers","volume":"710","author":"Petrushin","year":"1999","journal-title":"Proc. ANNIE"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0092070399272005"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(03)00099-2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5120\/11872-7667"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820699"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2925934"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-703"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383456"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747095"},{"key":"ref13","first-page":"12449","article-title":"wav2vec 2.0: A framework for selfsupervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Proc. NeurIPS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"volume-title":"A fine-tuned wav2vec 2.0\/hubert benchmark for speech emotion recognition, speaker verification and spoken language understanding","year":"2021","author":"Wang","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095036"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.084"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414470"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415081"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446945"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/97.736233"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2006.874403"},{"volume-title":"WebRTC VAD","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.23919\/eusipco54536.2021.9616082"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2944386"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.11591\/eei.v8i4.1646"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-1019"},{"volume-title":"Silero VAD: Pre-trained enterprise-grade voice activity detector (VAD) number detector and language classifier","year":"2021","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1446"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref37","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015","journal-title":"Proc. ICLR"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref39","article-title":"MUSAN: A music, speech, and noise corpus","author":"Snyder","year":"2015","journal-title":"arXiv"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-293"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249181.pdf?arnumber=11249181","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:50:33Z","timestamp":1764399033000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249181\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249181","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}