{"id":"https://openalex.org/W3161905931","doi":"https://doi.org/10.1109/icassp39728.2021.9414698","title":"Speech Emotion Recognition Based on Listener Adaptive Models","display_name":"Speech Emotion Recognition Based on Listener Adaptive Models","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161905931","doi":"https://doi.org/10.1109/icassp39728.2021.9414698","mag":"3161905931"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5061074419","display_name":"Atsushi Ando","orcid":"https://orcid.org/0000-0002-3971-0654"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi Ando","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060644399","display_name":"Ryo Masumura","orcid":"https://orcid.org/0000-0002-2415-4149"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Masumura","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103634381","display_name":"Hiroshi Sato","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Sato","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087290011","display_name":"Takafumi Moriya","orcid":"https://orcid.org/0000-0003-1942-7250"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takafumi Moriya","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033975068","display_name":"Takanori Ashihara","orcid":"https://orcid.org/0009-0003-4322-4127"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takanori Ashihara","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068604686","display_name":"Yusuke Ijima","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Ijima","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6274","last_page":"6278"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9994999766349792,"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":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7065352201461792},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6751298904418945},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6478118896484375},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6282822489738464},{"id":"https://openalex.org/keywords/emotion-perception","display_name":"Emotion perception","score":0.5750688910484314},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4826820194721222},{"id":"https://openalex.org/keywords/emotion-detection","display_name":"Emotion detection","score":0.42704012989997864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3123079538345337},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.29875263571739197},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.09190717339515686}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7065352201461792},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6751298904418945},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6478118896484375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6282822489738464},{"id":"https://openalex.org/C2776141551","wikidata":"https://www.wikidata.org/wiki/Q16000087","display_name":"Emotion perception","level":3,"score":0.5750688910484314},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4826820194721222},{"id":"https://openalex.org/C2988148770","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion detection","level":3,"score":0.42704012989997864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3123079538345337},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.29875263571739197},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.09190717339515686},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1597064524","https://openalex.org/W1997604360","https://openalex.org/W2029026153","https://openalex.org/W2146334809","https://openalex.org/W2171106464","https://openalex.org/W2403524927","https://openalex.org/W2523855251","https://openalex.org/W2552810951","https://openalex.org/W2597655663","https://openalex.org/W2625297138","https://openalex.org/W2742542661","https://openalex.org/W2753789229","https://openalex.org/W2786657259","https://openalex.org/W2787685498","https://openalex.org/W2801959488","https://openalex.org/W2889374687","https://openalex.org/W2889462515","https://openalex.org/W2889544113","https://openalex.org/W2892071465","https://openalex.org/W2936774411","https://openalex.org/W2937151161","https://openalex.org/W2963386218","https://openalex.org/W2972602947","https://openalex.org/W2972971501","https://openalex.org/W2973224100","https://openalex.org/W2999269393","https://openalex.org/W6713292810","https://openalex.org/W6735377749","https://openalex.org/W6744170603"],"related_works":["https://openalex.org/W3126677997","https://openalex.org/W1610857240","https://openalex.org/W4391307871","https://openalex.org/W4392502551","https://openalex.org/W2336827033","https://openalex.org/W2505228240","https://openalex.org/W4319430321","https://openalex.org/W3047499479","https://openalex.org/W4389296211","https://openalex.org/W2922915988"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,59],"novel":[4],"speech":[5,119],"emotion":[6,16,32,66,98,130],"recognition":[7,46,67,131],"scheme":[8],"that":[9,64,122],"can":[10,43,99],"deal":[11],"with":[12,35,75],"the":[13,23,36,40,45,82,89,93,106,109,123],"individuality":[14],"of":[15,26,69,92],"perception.":[17,50],"Most":[18],"conventional":[19,41],"methods":[20,42],"directly":[21],"model":[22,63,87],"majority":[24],"decision":[25],"multiple":[27],"listener\u2019s":[28],"perceived":[29,95,129],"emotions.":[30,96],"However,":[31],"perception":[33],"varies":[34],"listener,":[37],"which":[38],"means":[39],"mismatch":[44],"results":[47],"to":[48,53],"human":[49],"In":[51],"order":[52],"mitigate":[54],"this":[55],"problem,":[56],"we":[57],"propose":[58],"Listener":[60],"Adaptive":[61],"(LA)":[62],"reflects":[65],"criteria":[68],"each":[70],"listener.":[71],"One-hot":[72],"listener":[73],"codes":[74],"several":[76],"adaptation":[77],"layers":[78],"are":[79],"employed":[80],"in":[81,105,133],"LA":[83,86,107],"model.":[84],"The":[85],"yields":[88],"posterior":[90,110],"probabilities":[91,111],"listener-specific":[94],"Majority-voted":[97],"be":[100],"also":[101],"estimated":[102],"by":[103],"averaging,":[104],"model,":[108],"for":[112],"all":[113],"listeners.":[114],"Experiments":[115],"on":[116],"two":[117],"emotional":[118],"datasets":[120],"demonstrate":[121],"proposed":[124],"approach":[125],"offers":[126],"improved":[127],"listener-wise":[128],"performance":[132],"natural":[134],"speech.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
