{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T10:13:41Z","timestamp":1776939221624,"version":"3.51.4"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10445890","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"12126-12130","source":"Crossref","is-referenced-by-count":9,"title":["Learning Arousal-Valence Representation from Categorical Emotion Labels of Speech"],"prefix":"10.1109","author":[{"given":"Enting","family":"Zhou","sequence":"first","affiliation":[{"name":"University of Rochester,Department of Computer Science,USA,NY"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"You","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Rochester,Department of Electrical and Computer Engineering,USA,NY"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyao","family":"Duan","sequence":"additional","affiliation":[{"name":"University of Rochester,Department of Electrical and Computer Engineering,USA,NY"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.ps.30.020179.002523"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/0092-6566(77)90037-X"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2018.08.035"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/SMM.2018-5"},{"key":"ref5","article-title":"A fine-tuned wav2vec 2.0\/hubert benchmark for speech emotion recognition, speaker verification and spoken language understanding","author":"Wang","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-307"},{"key":"ref7","article-title":"Adjusting pleasure-arousal-dominance for continuous emotional text-to-speech synthesizer","author":"Rabiee","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413907"},{"key":"ref9","first-page":"247","article-title":"Mining valence, arousal, and dominance: possibilities for detecting burnout and productivity?","volume-title":"Proc. of the 13th international conference on mining software repositories","author":"M\u00e4ntyl\u00e4"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2008-192"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1037\/0022-3514.36.10.1152"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2020.14"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747754"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413910"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-1494"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2736999"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3225198"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICSMC.2012.6378303"},{"key":"ref22","article-title":"Umap: Uniform manifold approximation and projection for dimension reduction","author":"McInnes","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-446"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.2307\/2532051"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1896\/1\/012004"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10445890.pdf?arnumber=10445890","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:58:15Z","timestamp":1722574695000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10445890\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10445890","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}