{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:42:03Z","timestamp":1770918123177,"version":"3.50.1"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747197","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"3169-3173","source":"Crossref","is-referenced-by-count":24,"title":["Universal Paralinguistic Speech Representations Using self-Supervised Conformers"],"prefix":"10.1109","author":[{"given":"Joel","family":"Shor","sequence":"first","affiliation":[{"name":"Verily Life Sciences,Boston,USA"}]},{"given":"Aren","family":"Jansen","sequence":"additional","affiliation":[{"name":"Mountain View,California,USA"}]},{"given":"Wei","family":"Han","sequence":"additional","affiliation":[{"name":"Mountain View,California,USA"}]},{"given":"Daniel","family":"Park","sequence":"additional","affiliation":[{"name":"Mountain View,California,USA"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Mountain View,California,USA"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2857"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3078715"},{"key":"ref33","article-title":"Voxforge","author":"maclean","year":"2018"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-950","article-title":"Voxceleb: a large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"InterSpeech"},{"key":"ref31","first-page":"7669","article-title":"Libri-Light: A benchmark for ASR with limited or no supervision","author":"kahn","year":"2020","journal-title":"ICASSP"},{"key":"ref30","first-page":"776","article-title":"Audio set: An ontology and human-labeled dataset for audio events","author":"gemmeke","year":"2017","journal-title":"ICASSP"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-34255-5_17"},{"key":"ref36","first-page":"53","article-title":"Speaker-dependent audio-visual emotion recognition","author":"haq","year":"2009","journal-title":"AVSPN"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref34","article-title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","author":"warden","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2019.8925444"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1913"},{"key":"ref12","first-page":"12 449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref13","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref15","article-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","author":"zhang","year":"2020"},{"key":"ref16","article-title":"BigSSL: Exploring the frontier of large-scale semi-supervised learning for automatic speech recognition","author":"zhang","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2070"},{"key":"ref19","article-title":"The INTERSPEECH 2020 Computational Paralinguistics Challenge: Elderly emotion, Breathing & Masks","author":"schuller","year":"2020","journal-title":"InterSpeech"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461684"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref29","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume":"97","author":"tan","year":"2019","journal-title":"ICML ser Proceedings of Machine Learning Research"},{"key":"ref5","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2019"},{"key":"ref8","first-page":"609","article-title":"Look, listen and learn","author":"arandjelovic","year":"2017","journal-title":"ICCV"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2605"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413528"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054137"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1242"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2249"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-697"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","article-title":"IEMOCAP: Interactive emotional dyadic motion capture database","volume":"42","author":"busso","year":"2008","journal-title":"Language Resources and Evaluation"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1427"},{"key":"ref23","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume":"31","author":"jia","year":"2018","journal-title":"NeurIPS"},{"key":"ref26","article-title":"Do Vision Transformers see like convolutional neural networks?","author":"raghu","year":"2021"},{"key":"ref25","first-page":"3519","article-title":"Similarity of neural network representations revisited","author":"kornblith","year":"2019","journal-title":"ICML"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747197.pdf?arnumber=9747197","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:07:40Z","timestamp":1660594060000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747197\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747197","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}