{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T16:46:54Z","timestamp":1778604414138,"version":"3.51.4"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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":[[2024,12,3]]},"DOI":"10.1109\/apsipaasc63619.2025.10848943","type":"proceedings-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T18:37:05Z","timestamp":1738003025000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["Two-stage Framework for Robust Speech Emotion Recognition Using Target Speaker Extraction in Human Speech Noise Conditions"],"prefix":"10.1109","author":[{"given":"Jinyi","family":"Mi","sequence":"first","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohan","family":"Shi","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ding","family":"Ma","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiajun","family":"He","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takuya","family":"Fujimura","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3129340"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2020.103775"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11036-015-0586-3"},{"key":"ref4","first-page":"126","article-title":"On the ne-cessity and feasibility of detecting a driver\u2019s emotional state while driving","volume-title":"International Conference on Affective Computing and Intelligent Interaction","author":"Grimm"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2010.5547956"},{"key":"ref6","first-page":"22","article-title":"Emotion in speech: Recognition and application to call centers","volume-title":"Proceedings of artificial neural networks in engineering","volume":"710","author":"Petrushin"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.11.004"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICNC.2007.677"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/450\/1\/012053"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3245401"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095193"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095036"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.2478\/aoa-2013-0054"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-300"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2016.06.020"},{"key":"ref16","article-title":"On the effectiveness of asr representations in real-world noisy speech emotion recognition","author":"Shi","year":"2023"},{"key":"ref17","volume-title":"Listening: An introduction to the perception of auditory events","author":"Handel","year":"1993"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC53105.2022.9914718"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2922820"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054683"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747095"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414006"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"},{"key":"ref27","article-title":"Librimix: An open-source dataset for generalizable speech separation","author":"Cosentino","year":"2020"}],"event":{"name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","location":"Macau, Macao","start":{"date-parts":[[2024,12,3]]},"end":{"date-parts":[[2024,12,6]]}},"container-title":["2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10848542\/10848533\/10848943.pdf?arnumber=10848943","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T06:23:23Z","timestamp":1738045403000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10848943\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc63619.2025.10848943","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]}}}