{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:28:14Z","timestamp":1775230094887,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832143","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"518-525","source":"Crossref","is-referenced-by-count":12,"title":["Speech Emotion Recognition With ASR Transcripts: a Comprehensive Study on Word Error Rate and Fusion Techniques"],"prefix":"10.1109","author":[{"given":"Yuanchao","family":"Li","sequence":"first","affiliation":[{"name":"University of Edinburgh,Centre for Speech Technology Research"}]},{"given":"Peter","family":"Bell","sequence":"additional","affiliation":[{"name":"University of Edinburgh,Centre for Speech Technology Research"}]},{"given":"Catherine","family":"Lai","sequence":"additional","affiliation":[{"name":"University of Edinburgh,Centre for Speech Technology Research"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-2271"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3201"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639583"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1090"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2078"},{"key":"ref6","first-page":"28","article-title":"Releasing a thoroughly annotated and processed spontaneous emotional database: the fau aibo emotion corpus","volume-title":"Programme of the Workshop on Corpora for Research on Emotion and Affect","volume":"2008","author":"Batliner"},{"key":"ref7","article-title":"Cross-attention is not enough: Incongruity-aware dynamic hierarchical fusion for multimodal affect recognition","author":"Wang","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413710"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.143"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1149"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-158"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-411"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414880"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1723"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746289"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094839"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446548"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448130"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2736999"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1050"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3115\/1599081.1599192"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2024.104598"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372886"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2019.1667872"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1852"},{"issue":"6","key":"ref32","first-page":"7","article-title":"Alpaca: A strong, replicable instruction-following model","volume":"3","author":"Taori","year":"2023","journal-title":"Stanford Center for Research on Foundation Models"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.618"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832240"},{"key":"ref35","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference (LREC)","author":"Ardila"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832143.pdf?arnumber=10832143","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:08:01Z","timestamp":1737101281000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832143\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832143","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}