{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T11:42:06Z","timestamp":1779882126009,"version":"3.53.1"},"reference-count":41,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,19]]},"DOI":"10.1109\/slt48900.2021.9383456","type":"proceedings-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T20:46:54Z","timestamp":1616705214000},"page":"373-380","source":"Crossref","is-referenced-by-count":39,"title":["On the Use of Self-Supervised Pre-Trained Acoustic and Linguistic Features for Continuous Speech Emotion Recognition"],"prefix":"10.1109","author":[{"given":"Manon","family":"Macary","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marie","family":"Tahon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yannick","family":"Esteve","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anthony","family":"Rousseau","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2710"},{"key":"ref38","first-page":"9","article-title":"Asynchronous pipeline for processing huge corpora on medium to low resource infrastructures","author":"su\u00e1rez","year":"2019","journal-title":"Workshop on the Challenges in the Management of Large Corpora (CMLC-7)"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3347320.3357688"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3266302.3266316"},{"key":"ref31","article-title":"Audio AlBERT: A lite BERT for selfsupervised learning of audio representation","author":"chi","year":"2020"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"148","DOI":"10.21437\/Interspeech.2013-56","article-title":"The INTERSPEECH 2013 computational paralinguistics challenge: Social signals, conflict, emotion, autism","author":"schuller","year":"2013","journal-title":"Proc of Interspeech"},{"key":"ref37","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"liu","year":"2019"},{"key":"ref36","first-page":"45","article-title":"Software framework for topic modelling with large corpora","author":"?eh?rek","year":"2010","journal-title":"Proc of the LREC Workshop on New Challenges for NLP Frame-works"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60276-5_30"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.2307\/2532051"},{"key":"ref11","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1235"},{"key":"ref13","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc of the North American Chapter of the Association for Computational Linguistics (NAACL)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.05.025"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1441"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2018.2840738"},{"key":"ref17","first-page":"5753","article-title":"XLNet: Generalized autoregressive pre-training for language understanding","author":"yang","year":"2019","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2017.10.016"},{"key":"ref4","first-page":"1590","article-title":"AlloSat: A new call center french corpus for satisfaction and frustration analysis","author":"macary","year":"2020","journal-title":"Proc of Language Resources and Evaluation Conference (LREC) Virtual Conference"},{"key":"ref27","first-page":"2479","article-title":"FlauBERT: Unsupervised language model pre-training for French","author":"le","year":"2020","journal-title":"Proc of Language Resources and Evaluation Conference (LREC) Virtual Conference"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0539018405058216"},{"key":"ref6","first-page":"801","article-title":"Real-life emotions detection with lexical and paralinguistic cues on human-human call center dialogs","author":"devillers","year":"2006","journal-title":"Proc of Interspeech"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2944808"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553805"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICECCT.2015.7226047"},{"key":"ref2","first-page":"295","author":"russel","year":"1997","journal-title":"Reading Emotions from and into Faces Resurrecting a Dimensional-Contextual Perspective"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99579-3_21"},{"key":"ref1","first-page":"301","author":"ekman","year":"1999","journal-title":"Basic Emotions"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1835"},{"key":"ref22","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref24","author":"pustejovsky","year":"1996","journal-title":"Lexical Semantics The Problem of Polysemy Clarendon paperbacks"},{"key":"ref41","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref23","first-page":"199","article-title":"A sensitivity and performance analysis of Word2Vec applied to emotion state classification using a deep neural architecture","author":"pasti","year":"2019","journal-title":"Proc of the Distributed Computing and Artificial Intelligence Conference (DCAI)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.645"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1139"}],"event":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","location":"Shenzhen, China","start":{"date-parts":[[2021,1,19]]},"end":{"date-parts":[[2021,1,22]]}},"container-title":["2021 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9383468\/9383452\/09383456.pdf?arnumber=9383456","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T21:07:50Z","timestamp":1724706470000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9383456\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,19]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/slt48900.2021.9383456","relation":{},"subject":[],"published":{"date-parts":[[2021,1,19]]}}}