{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,3]],"date-time":"2025-05-03T07:23:54Z","timestamp":1746257034170,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095036","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":70,"title":["Exploring Wav2vec 2.0 Fine Tuning for Improved Speech Emotion Recognition"],"prefix":"10.1109","author":[{"given":"Li-Wei","family":"Chen","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,Language Technologies Institute"}]},{"given":"Alexander","family":"Rudnicky","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Language Technologies Institute"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1344"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1280"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1840"},{"key":"ref14","article-title":"Recognizing more emotions with less data using self-supervised transfer learning","volume":"abs 2011 5585","author":"boigne","year":"2020","journal-title":"ArXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref10","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":"ref2","article-title":"Speech emotion recognition using deep neural network and extreme learning machine","author":"han","year":"2014","journal-title":"Fifteenth Annual Conference of the International Speech Communication Association"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.02.013"},{"key":"ref17","article-title":"Don’t stop pretraining: Adapt language models to domains and tasks","author":"gururangan","year":"2020","journal-title":"Proceedings of ACL"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-703"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1121\/1.1352088"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-236"},{"key":"ref24","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"3rd International Conference on Learning Representations ICLR 2015 San Diego CA USA May 7-9 2015 Conference Track Proceedings"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref26","first-page":"21","article-title":"CNN+LSTM Architecture for Speech Emotion Recognition with Data Augmentation","author":"etienne","year":"2021","journal-title":"Proc Workshop on Speech Music and Mind (SMM 2018)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref20","first-page":"2357","article-title":"Advancing Multiple Instance Learning with Attention Modeling for Categorical Speech Emotion Recognition","author":"mao","year":"2021","journal-title":"Proc Interspeech 2020"},{"key":"ref22","first-page":"2613","article-title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","author":"park","year":"2021","journal-title":"Interspeech 2019"},{"key":"ref21","article-title":"Deep clustering for unsupervised learning of visual features","author":"caron","year":"2018","journal-title":"European Conference on Computer Vision"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-411"},{"key":"ref27","first-page":"374","article-title":"A Multi-Scale Fusion Framework for Bimodal Speech Emotion Recognition","author":"chen","year":"2021","journal-title":"Proc Interspeech 2020"},{"key":"ref8","article-title":"Albert: A lite bert for self-supervised learning of language representations","author":"lan","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref7","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref9","first-page":"3465","article-title":"wav2vec: Unsupervised Pre-Training for Speech Recognition","author":"schneider","year":"2021","journal-title":"Interspeech 2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659587"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391"},{"article-title":"Surrey audio-visual expressed emotion (savee) database","year":"2011","author":"jackson","key":"ref5"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095036.pdf?arnumber=10095036","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T14:03:07Z","timestamp":1700488987000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095036\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095036","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}