{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T16:26:07Z","timestamp":1783787167486,"version":"3.55.0"},"reference-count":22,"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"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10887715","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Extending Whisper for Emotion Prediction Using Word-level Pseudo Labels"],"prefix":"10.1109","author":[{"given":"Chin Yuen","family":"Kwok","sequence":"first","affiliation":[{"name":"Nanyang Technological University,Digital Trust Centre,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheng","family":"Li","sequence":"additional","affiliation":[{"name":"National Institute of Information & Communications Technology (NICT),Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia Qi","family":"Yip","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,College of Computing and Data Science,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenhui","family":"Chu","sequence":"additional","affiliation":[{"name":"Kyoto University,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tatsuya","family":"Kawahara","sequence":"additional","affiliation":[{"name":"Kyoto University,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eng Siong","family":"Chng","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,College of Computing and Data Science,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Byte pair encoding: A text compression scheme that accelerates pattern matching","author":"Shibata","year":"1999"},{"key":"ref2","article-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models","author":"Chu","year":"2023"},{"key":"ref3","article-title":"Salmonn: Towards generic hearing abilities for large language models","author":"Tang","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448130"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446548"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447667"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2017.8273599"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1968"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3083821"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00380"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446812"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.931"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.60"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref16","article-title":"Common voice: A massively-multilingual speech corpus","author":"Ardila","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3487410"},{"key":"ref18","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref19","first-page":"28 492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446997"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP48485.2024.10446548","article-title":"Mf-aed-aec: Speech emotion recognition by leveraging multimodal fusion, asr error detection, and asr error correction","author":"He","year":"2024"},{"key":"ref22","article-title":"Fine-grained disentangled representation learning for multimodal emotion recognition","author":"Sun","year":"2023"}],"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\/10887715.pdf?arnumber=10887715","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:57Z","timestamp":1774416357000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887715\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887715","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}