{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:29:19Z","timestamp":1775230159232,"version":"3.50.1"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10023428","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T13:54:03Z","timestamp":1674827643000},"page":"868-875","source":"Crossref","is-referenced-by-count":25,"title":["Exploration of a Self-Supervised Speech Model: A Study on Emotional Corpora"],"prefix":"10.1109","author":[{"given":"Yuanchao","family":"Li","sequence":"first","affiliation":[{"name":"University of Edinburgh,Centre for Speech Technology Research"}]},{"given":"Yumnah","family":"Mohamied","sequence":"additional","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":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2684"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"2639","DOI":"10.1162\/0899766042321814","article-title":"Canonical correlation analysis: An overview with application to learning methods","volume":"16","author":"david","year":"2004","journal-title":"Neural Computation"},{"key":"ref12","first-page":"2803","article-title":"Im-proved End-to-End Speech Emotion Recognition Using Self Attention Mechanism and Multitask Learning","author":"li","year":"2019","journal-title":"InterSpeech"},{"key":"ref34","article-title":"Recognizing more emotions with less data using self-supervised transfer learning","author":"boigne","year":"2020","journal-title":"ar Xiv preprint"},{"key":"ref15","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-74"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref31","article-title":"Exploring Wav2vec 2.0 fine-tuning for improved speech emotion recognition","author":"chen","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846260"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1852"},{"key":"ref10","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"International Conference on Machine Learning"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747417"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-49127-9"},{"key":"ref1","author":"fant","year":"1973","journal-title":"Speech Sounds and Features"},{"key":"ref17","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":"Ad-vances in Neural Information Processing Systems"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367152"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367261"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref24","first-page":"arxiv-1807","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018","journal-title":"ArXiv e-prints"},{"key":"ref23","article-title":"Non-autoregressive predictive coding for learning speech representations from local dependencies","author":"liu","year":"2020","journal-title":"ar Xiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref20","article-title":"Exploring wav2vec 2.0 on speaker verification and language identification","author":"fan","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref41","article-title":"Interactional and pragmatics-related prosodic patterns in Mandarin dialog","author":"nigel","year":"2016","journal-title":"Speech Prosody"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1228"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-703"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746289"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref8","first-page":"17","article-title":"Word-level emotion recognition using high-level features","author":"johanna","year":"2014","journal-title":"International Conference on Intelligent Text Processing and Computational Linguistics"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.11.006"},{"key":"ref9","article-title":"Dialog act classification from prosodic features using support vec-tor machines","author":"fernandez","year":"2002","journal-title":"Speech Prosody 2002 International Conference"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S1071-5819(02)00141-6"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1037\/0033-2909.97.3.412","article-title":"Communicating emotion: The role of prosodic features","volume":"97","author":"robert","year":"1985","journal-title":"Psychological Bulletin"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1121\/1.399423"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2051872"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","location":"Doha, Qatar","start":{"date-parts":[[2023,1,9]]},"end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10023428.pdf?arnumber=10023428","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,20]],"date-time":"2023-02-20T17:08:42Z","timestamp":1676912922000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10023428\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10023428","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}