{"id":"https://openalex.org/W3101317406","doi":"https://doi.org/10.1109/slt48900.2021.9383456","title":"On the Use of Self-Supervised Pre-Trained Acoustic and Linguistic Features for Continuous Speech Emotion Recognition","display_name":"On the Use of Self-Supervised Pre-Trained Acoustic and Linguistic Features for Continuous Speech Emotion Recognition","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3101317406","doi":"https://doi.org/10.1109/slt48900.2021.9383456","mag":"3101317406"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383456","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383456","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.09212","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089715431","display_name":"Manon Macary","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138976","display_name":"Association for Language Learning","ror":"https://ror.org/0455ncp47","country_code":"GB","type":"other","lineage":["https://openalex.org/I4210138976"]},{"id":"https://openalex.org/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]},{"id":"https://openalex.org/I234216984","display_name":"Universit\u00e9 Nantes Angers Le Mans","ror":"https://ror.org/0406t3m57","country_code":"FR","type":"education","lineage":["https://openalex.org/I234216984"]}],"countries":["FR","GB"],"is_corresponding":true,"raw_author_name":"Manon Macary","raw_affiliation_strings":["Allo-Media","LIUM, Le Mans Universit\u00e9, France","Le Mans Universit\u00e9,LIUM,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allo-Media","institution_ids":["https://openalex.org/I4210138976"]},{"raw_affiliation_string":"LIUM, Le Mans Universit\u00e9, France","institution_ids":["https://openalex.org/I234216984","https://openalex.org/I4210108471"]},{"raw_affiliation_string":"Le Mans Universit\u00e9,LIUM,France","institution_ids":["https://openalex.org/I4210108471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028709353","display_name":"Marie Tahon","orcid":"https://orcid.org/0000-0002-6782-0332"},"institutions":[{"id":"https://openalex.org/I234216984","display_name":"Universit\u00e9 Nantes Angers Le Mans","ror":"https://ror.org/0406t3m57","country_code":"FR","type":"education","lineage":["https://openalex.org/I234216984"]},{"id":"https://openalex.org/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Marie Tahon","raw_affiliation_strings":["LIUM, Le Mans Universit\u00e9, France","Le Mans Universit\u00e9,LIUM,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIUM, Le Mans Universit\u00e9, France","institution_ids":["https://openalex.org/I234216984","https://openalex.org/I4210108471"]},{"raw_affiliation_string":"Le Mans Universit\u00e9,LIUM,France","institution_ids":["https://openalex.org/I4210108471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081852717","display_name":"Yannick Est\u00e8ve","orcid":"https://orcid.org/0000-0002-3656-8883"},"institutions":[{"id":"https://openalex.org/I4210119991","display_name":"Laboratoire Informatique d'Avignon","ror":"https://ror.org/02n399288","country_code":"FR","type":"facility","lineage":["https://openalex.org/I198415970","https://openalex.org/I4210119991"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yannick Esteve","raw_affiliation_strings":["LIA, Avignon Universit\u00e9, France","Avignon Universit\u00e9,LIA,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIA, Avignon Universit\u00e9, France","institution_ids":["https://openalex.org/I4210119991"]},{"raw_affiliation_string":"Avignon Universit\u00e9,LIA,France","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063176676","display_name":"A. Rousseau","orcid":"https://orcid.org/0000-0002-5074-824X"},"institutions":[{"id":"https://openalex.org/I4210138976","display_name":"Association for Language Learning","ror":"https://ror.org/0455ncp47","country_code":"GB","type":"other","lineage":["https://openalex.org/I4210138976"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Anthony Rousseau","raw_affiliation_strings":["Allo-Media"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allo-Media","institution_ids":["https://openalex.org/I4210138976"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5089715431"],"corresponding_institution_ids":["https://openalex.org/I234216984","https://openalex.org/I4210108471","https://openalex.org/I4210138976"],"apc_list":null,"apc_paid":null,"fwci":0.3087,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.50669792,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"373","last_page":"380"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6744545102119446},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5895416736602783},{"id":"https://openalex.org/keywords/valence","display_name":"Valence (chemistry)","score":0.5756308436393738},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.5230492353439331},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5021231174468994},{"id":"https://openalex.org/keywords/concordance-correlation-coefficient","display_name":"Concordance correlation coefficient","score":0.47690248489379883},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.47026997804641724},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.4686151146888733},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46281325817108154},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4339880347251892},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.41856810450553894},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41591671109199524},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.41506972908973694},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4107479751110077},{"id":"https://openalex.org/keywords/arousal","display_name":"Arousal","score":0.41068243980407715},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.18218296766281128},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13066905736923218},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08925333619117737}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6744545102119446},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5895416736602783},{"id":"https://openalex.org/C168900304","wikidata":"https://www.wikidata.org/wiki/Q171407","display_name":"Valence (chemistry)","level":2,"score":0.5756308436393738},{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.5230492353439331},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5021231174468994},{"id":"https://openalex.org/C2781059462","wikidata":"https://www.wikidata.org/wiki/Q5158906","display_name":"Concordance correlation coefficient","level":2,"score":0.47690248489379883},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.47026997804641724},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.4686151146888733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46281325817108154},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4339880347251892},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.41856810450553894},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41591671109199524},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.41506972908973694},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4107479751110077},{"id":"https://openalex.org/C36951298","wikidata":"https://www.wikidata.org/wiki/Q379784","display_name":"Arousal","level":2,"score":0.41068243980407715},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.18218296766281128},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13066905736923218},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08925333619117737},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/slt48900.2021.9383456","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383456","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.09212","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.09212","pdf_url":"https://arxiv.org/pdf/2011.09212","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-03003469v1","is_oa":false,"landing_page_url":"https://hal.science/hal-03003469","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Spoken Language Technology Workshop, Jan 2021, Virtual, China","raw_type":"Conference papers"},{"id":"doi:10.48550/arxiv.2011.09212","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.09212","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/4mtd-9f91","is_oa":true,"landing_page_url":"https://doi.org/10.17023/4mtd-9f91","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.09212","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.09212","pdf_url":"https://arxiv.org/pdf/2011.09212","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W168564468","https://openalex.org/W1494198834","https://openalex.org/W1876223856","https://openalex.org/W2045528981","https://openalex.org/W2085662862","https://openalex.org/W2102998034","https://openalex.org/W2144005487","https://openalex.org/W2153579005","https://openalex.org/W2158943324","https://openalex.org/W2239141610","https://openalex.org/W2313339984","https://openalex.org/W2621367454","https://openalex.org/W2765815408","https://openalex.org/W2798717312","https://openalex.org/W2799473636","https://openalex.org/W2884001105","https://openalex.org/W2897444637","https://openalex.org/W2910165986","https://openalex.org/W2948902769","https://openalex.org/W2953356739","https://openalex.org/W2956065735","https://openalex.org/W2963341956","https://openalex.org/W2963854351","https://openalex.org/W2965373594","https://openalex.org/W2970597249","https://openalex.org/W2970971581","https://openalex.org/W2972944488","https://openalex.org/W2973049979","https://openalex.org/W2981677410","https://openalex.org/W2982223350","https://openalex.org/W2986154550","https://openalex.org/W2990842302","https://openalex.org/W2995181338","https://openalex.org/W3021934733","https://openalex.org/W3025035610","https://openalex.org/W3032532958","https://openalex.org/W3049256661","https://openalex.org/W3088876910","https://openalex.org/W3101648800","https://openalex.org/W6682691769","https://openalex.org/W6683165025","https://openalex.org/W6755207826","https://openalex.org/W6763701032","https://openalex.org/W6765850356","https://openalex.org/W6766673545","https://openalex.org/W6766978945","https://openalex.org/W6771509786","https://openalex.org/W6776713644","https://openalex.org/W6777232839"],"related_works":["https://openalex.org/W3122349645","https://openalex.org/W3122100772","https://openalex.org/W3117814038","https://openalex.org/W2944787130","https://openalex.org/W2992984162","https://openalex.org/W2936173226","https://openalex.org/W3162811262","https://openalex.org/W3003111647","https://openalex.org/W2939224318","https://openalex.org/W2027052150","https://openalex.org/W2107081756","https://openalex.org/W2928112693","https://openalex.org/W3094312606","https://openalex.org/W2950785196","https://openalex.org/W3213710575","https://openalex.org/W3169893188","https://openalex.org/W3091191991","https://openalex.org/W2773515538","https://openalex.org/W2963447013","https://openalex.org/W3194235020"],"abstract_inverted_index":{"Pre-training":[0],"for":[1],"feature":[2],"extraction":[3],"is":[4,94],"an":[5],"increasingly":[6],"studied":[7],"approach":[8],"to":[9,32,38,97],"get":[10],"better":[11],"continuous":[12,40,100],"representations":[13],"of":[14,61,88,109,131,134],"audio":[15],"and":[16,26,57,70,90],"text":[17],"content.":[18],"In":[19],"the":[20,54,59,62,74,80,85,115,146],"present":[21],"work,":[22],"we":[23,125],"use":[24,87],"wav2vec":[25,89],"camemBERT":[27],"as":[28],"self-supervised":[29],"learned":[30],"models":[31],"represent":[33],"our":[34,121],"data":[35],"in":[36,139],"order":[37],"perform":[39],"emotion":[41],"recognition":[42],"from":[43],"speech":[44],"(SER)":[45],"on":[46,58,67,145],"AlloSat,":[47],"a":[48,106,128],"large":[49],"French":[50],"emotional":[51],"database":[52],"describing":[53],"satisfaction":[55],"dimension,":[56],"state":[60],"art":[63],"corpus":[64],"SEWA":[65],"focusing":[66],"valence,":[68],"arousal":[69],"liking":[71],"dimensions.":[72],"To":[73],"authors'":[75],"knowledge,":[76],"this":[77],"paper":[78],"presents":[79],"first":[81],"study":[82],"showing":[83],"that":[84,124],"joint":[86],"BERT-like":[91],"pre-trained":[92],"features":[93],"very":[95],"relevant":[96],"deal":[98],"with":[99,141],"SER":[101],"task,":[102],"usually":[103],"characterized":[104],"by":[105,114],"small":[107],"amount":[108],"labeled":[110],"training":[111],"data.":[112],"Evaluated":[113],"well-known":[116],"concordance":[117],"correlation":[118],"coefficient":[119],"(CCC),":[120],"experiments":[122],"show":[123],"can":[126],"reach":[127],"CCC":[129],"value":[130],"0.825":[132],"instead":[133],"0.592":[135],"when":[136],"using":[137],"MFCC":[138],"conjunction":[140],"word2vec":[142],"word":[143],"embedding":[144],"AlloSat":[147],"dataset.":[148]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}