{"id":"https://openalex.org/W4385484923","doi":"https://doi.org/10.1109/icasspw59220.2023.10193151","title":"A Vector Quantized Masked Autoencoder for Speech Emotion Recognition","display_name":"A Vector Quantized Masked Autoencoder for Speech Emotion Recognition","publication_year":2023,"publication_date":"2023-06-04","ids":{"openalex":"https://openalex.org/W4385484923","doi":"https://doi.org/10.1109/icasspw59220.2023.10193151"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw59220.2023.10193151","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10193151","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021724743","display_name":"Samir Sadok","orcid":"https://orcid.org/0009-0007-5956-4133"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210100151","display_name":"Institut d'\u00c9lectronique et des Technologies du num\u00e9Rique","ror":"https://ror.org/013q33h79","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I28221208","https://openalex.org/I4210095849","https://openalex.org/I4210100151","https://openalex.org/I56067802","https://openalex.org/I97188460"]},{"id":"https://openalex.org/I4210107720","display_name":"CentraleSup\u00e9lec","ror":"https://ror.org/019tcpt25","country_code":"FR","type":"facility","lineage":["https://openalex.org/I277688954","https://openalex.org/I4210107720"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Samir Sadok","raw_affiliation_strings":["CentraleSupélec, IETR UMR CNRS 6164,France","CentraleSup\u00e9lec [campus de Rennes] (Campus de Rennes, Av. de la Boulaie, 35510 Cesson-S\u00e9vign\u00e9 - France)","IETR - Institut d'\u00c9lectronique et des Technologies du num\u00e9Rique (Campus de Beaulieu B\u00e2timent 11D 263 Av.G\u00e9n\u00e9ral Leclerc-CS 74205 35042 Rennes Cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CentraleSupélec, IETR UMR CNRS 6164,France","institution_ids":["https://openalex.org/I4210107720","https://openalex.org/I1294671590","https://openalex.org/I4210100151"]},{"raw_affiliation_string":"CentraleSup\u00e9lec [campus de Rennes] (Campus de Rennes, Av. de la Boulaie, 35510 Cesson-S\u00e9vign\u00e9 - France)","institution_ids":["https://openalex.org/I4210107720"]},{"raw_affiliation_string":"IETR - Institut d'\u00c9lectronique et des Technologies du num\u00e9Rique (Campus de Beaulieu B\u00e2timent 11D 263 Av.G\u00e9n\u00e9ral Leclerc-CS 74205 35042 Rennes Cedex - France)","institution_ids":["https://openalex.org/I4210100151"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045593473","display_name":"Simon Leglaive","orcid":"https://orcid.org/0000-0002-8219-1298"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210100151","display_name":"Institut d'\u00c9lectronique et des Technologies du num\u00e9Rique","ror":"https://ror.org/013q33h79","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I28221208","https://openalex.org/I4210095849","https://openalex.org/I4210100151","https://openalex.org/I56067802","https://openalex.org/I97188460"]},{"id":"https://openalex.org/I4210107720","display_name":"CentraleSup\u00e9lec","ror":"https://ror.org/019tcpt25","country_code":"FR","type":"facility","lineage":["https://openalex.org/I277688954","https://openalex.org/I4210107720"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Simon Leglaive","raw_affiliation_strings":["CentraleSupélec, IETR UMR CNRS 6164,France","IETR - Institut d'\u00c9lectronique et des Technologies du num\u00e9Rique (Campus de Beaulieu B\u00e2timent 11D 263 Av.G\u00e9n\u00e9ral Leclerc-CS 74205 35042 Rennes Cedex - France)","CentraleSup\u00e9lec [campus de Rennes] (Campus de Rennes, Av. de la Boulaie, 35510 Cesson-S\u00e9vign\u00e9 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CentraleSupélec, IETR UMR CNRS 6164,France","institution_ids":["https://openalex.org/I4210107720","https://openalex.org/I1294671590","https://openalex.org/I4210100151"]},{"raw_affiliation_string":"IETR - Institut d'\u00c9lectronique et des Technologies du num\u00e9Rique (Campus de Beaulieu B\u00e2timent 11D 263 Av.G\u00e9n\u00e9ral Leclerc-CS 74205 35042 Rennes Cedex - France)","institution_ids":["https://openalex.org/I4210100151"]},{"raw_affiliation_string":"CentraleSup\u00e9lec [campus de Rennes] (Campus de Rennes, Av. de la Boulaie, 35510 Cesson-S\u00e9vign\u00e9 - France)","institution_ids":["https://openalex.org/I4210107720"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040347439","display_name":"Renaud S\u00e9guier","orcid":"https://orcid.org/0000-0001-7199-7563"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210100151","display_name":"Institut d'\u00c9lectronique et des Technologies du num\u00e9Rique","ror":"https://ror.org/013q33h79","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I28221208","https://openalex.org/I4210095849","https://openalex.org/I4210100151","https://openalex.org/I56067802","https://openalex.org/I97188460"]},{"id":"https://openalex.org/I4210107720","display_name":"CentraleSup\u00e9lec","ror":"https://ror.org/019tcpt25","country_code":"FR","type":"facility","lineage":["https://openalex.org/I277688954","https://openalex.org/I4210107720"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Renaud S\u00e9guier","raw_affiliation_strings":["CentraleSupélec, IETR UMR CNRS 6164,France","CentraleSup\u00e9lec [campus de Rennes] (Campus de Rennes, Av. de la Boulaie, 35510 Cesson-S\u00e9vign\u00e9 - France)","IETR - Institut d'\u00c9lectronique et des Technologies du num\u00e9Rique (Campus de Beaulieu B\u00e2timent 11D 263 Av.G\u00e9n\u00e9ral Leclerc-CS 74205 35042 Rennes Cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CentraleSupélec, IETR UMR CNRS 6164,France","institution_ids":["https://openalex.org/I4210107720","https://openalex.org/I1294671590","https://openalex.org/I4210100151"]},{"raw_affiliation_string":"CentraleSup\u00e9lec [campus de Rennes] (Campus de Rennes, Av. de la Boulaie, 35510 Cesson-S\u00e9vign\u00e9 - France)","institution_ids":["https://openalex.org/I4210107720"]},{"raw_affiliation_string":"IETR - Institut d'\u00c9lectronique et des Technologies du num\u00e9Rique (Campus de Beaulieu B\u00e2timent 11D 263 Av.G\u00e9n\u00e9ral Leclerc-CS 74205 35042 Rennes Cedex - France)","institution_ids":["https://openalex.org/I4210100151"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.0344,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.98059043,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"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"}},{"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/T10860","display_name":"Speech and Audio Processing","score":0.9986000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.9473394155502319},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6986100077629089},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6568728089332581},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6472009420394897},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6199007630348206},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.560343325138092},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5284362435340881},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.48740437626838684},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4814950227737427}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.9473394155502319},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6986100077629089},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6568728089332581},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6472009420394897},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6199007630348206},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.560343325138092},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5284362435340881},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.48740437626838684},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4814950227737427},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw59220.2023.10193151","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10193151","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W2074788634","https://openalex.org/W2146334809","https://openalex.org/W2622263826","https://openalex.org/W2752796333","https://openalex.org/W2803193013","https://openalex.org/W2808631503","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2963799213","https://openalex.org/W2997399314","https://openalex.org/W3094502228","https://openalex.org/W3122349645","https://openalex.org/W3184087575","https://openalex.org/W3197642003","https://openalex.org/W3206192140","https://openalex.org/W3206395542","https://openalex.org/W3206996142","https://openalex.org/W3211224152","https://openalex.org/W4214673031","https://openalex.org/W4285483774","https://openalex.org/W4289644862","https://openalex.org/W4297841853","https://openalex.org/W4311137818","https://openalex.org/W4312292725","https://openalex.org/W4313156423","https://openalex.org/W4385245566","https://openalex.org/W6739622702","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6784333009","https://openalex.org/W6798617289","https://openalex.org/W6802517614","https://openalex.org/W6802546489","https://openalex.org/W6803378298","https://openalex.org/W6841478064"],"related_works":["https://openalex.org/W2669956259","https://openalex.org/W4249005693","https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W2983142544","https://openalex.org/W2891059443","https://openalex.org/W4281663961","https://openalex.org/W3208888551","https://openalex.org/W4313561566","https://openalex.org/W3208386644"],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2],"seen":[3],"remarkable":[4],"progress":[5],"in":[6,14,29,82,125],"speech":[7,56,68,110],"emotion":[8],"recognition":[9],"(SER),":[10],"thanks":[11],"to":[12,41,64],"advances":[13],"deep":[15],"learning":[16,33],"techniques.":[17],"However,":[18],"the":[19,30,50,83,97,103,117],"limited":[20],"availability":[21],"of":[22,87],"labeled":[23],"data":[24],"remains":[25],"a":[26,38,58,76,88],"significant":[27],"challenge":[28],"field.":[31],"Self-supervised":[32],"has":[34],"recently":[35],"emerged":[36],"as":[37],"promising":[39],"solution":[40],"address":[42],"this":[43,46],"challenge.":[44],"In":[45],"paper,":[47],"we":[48],"propose":[49],"vector":[51,89],"quantized":[52,90],"masked":[53,77],"autoencoder":[54,78],"for":[55],"(VQ-MAE-S),":[57],"self-supervised":[59],"model":[60,72],"that":[61,80,96],"is":[62,73],"fine-tuned":[63,107],"recognize":[65],"emotions":[66],"from":[67],"signals.":[69],"The":[70],"VQ-MAE-S":[71,99],"based":[74],"on":[75,102,108,116],"(MAE)":[79],"operates":[81],"discrete":[84],"latent":[85],"space":[86],"variational":[91],"autoencoder.":[92],"Experimental":[93],"results":[94],"show":[95],"proposed":[98],"model,":[100],"pre-trained":[101],"VoxCeleb2":[104],"dataset":[105],"and":[106,121],"emotional":[109],"data,":[111],"outperforms":[112],"an":[113],"MAE":[114],"working":[115],"raw":[118],"spectrogram":[119],"representation":[120],"other":[122],"state-of-the-art":[123],"methods":[124],"SER.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}