{"id":"https://openalex.org/W4287212294","doi":"https://doi.org/10.48550/arxiv.2104.07288","title":"Speaker Attentive Speech Emotion Recognition","display_name":"Speaker Attentive Speech Emotion Recognition","publication_year":2021,"publication_date":"2021-04-15","ids":{"openalex":"https://openalex.org/W4287212294","doi":"https://doi.org/10.48550/arxiv.2104.07288"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2104.07288","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.07288","pdf_url":"https://arxiv.org/pdf/2104.07288","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.07288","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080970482","display_name":"Cl\u00e9ment Le Moine Veillon","orcid":"https://orcid.org/0000-0001-5500-5595","observed_orcids":["https://orcid.org/0000-0001-5500-5595"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moine, Cl\u00e9ment Le","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042745853","display_name":"Nicolas Obin","orcid":"https://orcid.org/0000-0002-5236-5306","observed_orcids":["https://orcid.org/0000-0002-5236-5306"]},"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/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4389425508","display_name":"Sciences et Technologies de la Musique et du Son","ror":"https://ror.org/025xvn046","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I2802818602","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4210102700","https://openalex.org/I4389425508"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Obin, Nicolas","raw_affiliation_strings":["STMS Lab IRCAM , CNRS , Sorbonne Universit\u00e9 , Paris , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STMS Lab IRCAM , CNRS , Sorbonne Universit\u00e9 , Paris , France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4389425508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065828059","display_name":"Axel R\u00f6ebel","orcid":"https://orcid.org/0000-0001-6136-4391","observed_orcids":["https://orcid.org/0000-0001-6136-4391"]},"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/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4389425508","display_name":"Sciences et Technologies de la Musique et du Son","ror":"https://ror.org/025xvn046","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I2802818602","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4210102700","https://openalex.org/I4389425508"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Roebel, Axel","raw_affiliation_strings":["STMS Lab IRCAM , CNRS , Sorbonne Universit\u00e9 , Paris , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STMS Lab IRCAM , CNRS , Sorbonne Universit\u00e9 , Paris , France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4389425508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9976000189781189,"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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9976000189781189,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.0019000000320374966,"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":0.00019999999494757503,"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/speech-emotion-recognition","display_name":"speech emotion recognition","score":0.9750000238418579},{"id":"https://openalex.org/keywords/speaker-identity","display_name":"speaker identity","score":0.48399999737739563},{"id":"https://openalex.org/keywords/attention-based-recurrent-neural-network","display_name":"attention-based recurrent neural network","score":0.6539999842643738},{"id":"https://openalex.org/keywords/speaker-adaptation","display_name":"speaker adaptation","score":0.48100000619888306},{"id":"https://openalex.org/keywords/iemocap","display_name":"IEMOCAP","score":0.890999972820282},{"id":"https://openalex.org/keywords/social-attitudes","display_name":"social attitudes","score":0.44999998807907104}],"concepts":[{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.7561615705490112},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6866206526756287},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.682712972164154},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.6145910024642944},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5827698111534119},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5765841007232666},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5643904209136963},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5522944927215576},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.49010953307151794},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4482656419277191},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.43875280022621155},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41675862669944763},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30957236886024475},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.29766690731048584},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2965649366378784},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2104.07288","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.07288","pdf_url":"https://arxiv.org/pdf/2104.07288","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"doi:10.48550/arxiv.2104.07288","doi":"https://doi.org/10.48550/arxiv.2104.07288","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.07288","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.07288","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.07288","pdf_url":"https://arxiv.org/pdf/2104.07288","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4287212294.pdf","grobid_xml":"https://content.openalex.org/works/W4287212294.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3169022486","https://openalex.org/W2049462786","https://openalex.org/W4387807210","https://openalex.org/W3161428216","https://openalex.org/W4312095979","https://openalex.org/W2972498864","https://openalex.org/W4309210550","https://openalex.org/W2912728762","https://openalex.org/W2807062934","https://openalex.org/W4386921230"],"abstract_inverted_index":{"Speech":[0],"Emotion":[1],"Recognition":[2],"(SER)":[3],"task":[4],"has":[5],"known":[6],"significant":[7],"improvements":[8],"over":[9],"the":[10,14,23,58,62,88,109,122,125,130],"last":[11],"years":[12],"with":[13],"advent":[15],"of":[16,60,74,108,124,135],"Deep":[17],"Neural":[18],"Networks":[19],"(DNNs).":[20],"However,":[21],"even":[22],"most":[24],"successful":[25],"methods":[26],"are":[27],"still":[28],"rather":[29],"failing":[30],"when":[31,45],"adaptation":[32],"to":[33,42,47,80,100,103],"specific":[34],"speakers":[35],"and":[36,82,118,128],"scenarios":[37],"is":[38,71,98],"needed,":[39],"inevitably":[40],"leading":[41],"poorer":[43],"performances":[44],"compared":[46],"humans.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52],"present":[53],"novel":[54],"work":[55],"based":[56],"on":[57,105,113],"idea":[59],"teaching":[61],"emotion":[63,83],"recognition":[64],"network":[65],"about":[66],"speaker":[67,81],"identity.":[68],"Our":[69],"system":[70],"a":[72,91],"combination":[73],"two":[75],"ACRNN":[76],"classifiers":[77],"respectively":[78],"dedicated":[79],"recognition.":[84],"The":[85],"first":[86],"informs":[87],"latter":[89],"through":[90],"Self":[92],"Speaker":[93],"Attention":[94],"(SSA)":[95],"mechanism":[96],"that":[97],"shown":[99],"considerably":[101],"help":[102],"focus":[104],"emotional":[106],"information":[107],"speech":[110],"signal.":[111],"Experiments":[112],"social":[114],"attitudes":[115],"database":[116],"Att-HACK":[117],"IEMOCAP":[119],"corpus":[120],"demonstrate":[121],"effectiveness":[123],"proposed":[126],"method":[127],"achieve":[129],"state-of-the-art":[131],"performance":[132],"in":[133],"terms":[134],"unweighted":[136],"average":[137],"recall.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2022-07-25T00:00:00"}
