{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:21:58Z","timestamp":1775229718394,"version":"3.50.1"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890558","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Stimulus Modality Matters: Impact of Perceptual Evaluations from Different Modalities on Speech Emotion Recognition System Performance"],"prefix":"10.1109","author":[{"given":"Huang-Cheng","family":"Chou","sequence":"first","affiliation":[{"name":"National Tsing Hua University,Department of Electrical Engineering,Hsinchu City,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haibin","family":"Wu","sequence":"additional","affiliation":[{"name":"National Taiwan University,Department of Electrical Engineering,Taipei City,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chi-Chun","family":"Lee","sequence":"additional","affiliation":[{"name":"National Tsing Hua University,Department of Electrical Engineering,Hsinchu City,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2736999"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11012"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1113"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11031-011-9206-0"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3461702.3462609"},{"key":"ref9","first-page":"392","article-title":"A BERT based dual-channel explainable text emotion recognition system","volume-title":"Neural Networks","volume":"150","author":"Kumar","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/SMM.2019-3"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461866"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/icme51207.2021.9428219"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3234777"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3614110"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3369726"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746990"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2020.11.004"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832296"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9053176"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1228"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-349"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-143"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref28","first-page":"1298","article-title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","volume-title":"Proceedings of the 39th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"162","author":"Baevski"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref30","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref31","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"Baevski","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-236"},{"key":"ref34","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00949"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/odyssey.2024-35"},{"key":"ref37","article-title":"Macro f1 and macro f1","author":"Opitz","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1201.0490"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3411290"},{"key":"ref40","article-title":"Confidence Intervals for evaluation in machine learning","volume-title":"Computer software","author":"Ferrer","year":"2024"},{"key":"ref41","article-title":"Decoupled Weight Decay Regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4g18.8"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.2307\/2532051"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890558.pdf?arnumber=10890558","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:58Z","timestamp":1774416178000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890558\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890558","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}