{"id":"https://openalex.org/W2981664983","doi":"https://doi.org/10.1109/expat.2019.8876534","title":"Importance of speaker specific speech features for emotion recognition","display_name":"Importance of speaker specific speech features for emotion recognition","publication_year":2019,"publication_date":"2019-06-01","ids":{"openalex":"https://openalex.org/W2981664983","doi":"https://doi.org/10.1109/expat.2019.8876534","mag":"2981664983"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/expat.2019.8876534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5063036404","display_name":"Gustavo Assun\u00e7\u00e3o","orcid":"https://orcid.org/0000-0003-4015-4111"},"institutions":[{"id":"https://openalex.org/I76903346","display_name":"University of Coimbra","ror":"https://ror.org/04z8k9a98","country_code":"PT","type":"funder","lineage":["https://openalex.org/I76903346"]},{"id":"https://openalex.org/I4210125590","display_name":"Institute for Systems Engineering and Computers","ror":"https://ror.org/033wn8m60","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Gustavo Assuncao","raw_affiliation_strings":["Institute of Systems and Robotics, University of Coimbra, Coimbra, Portugal"],"affiliations":[{"raw_affiliation_string":"Institute of Systems and Robotics, University of Coimbra, Coimbra, Portugal","institution_ids":["https://openalex.org/I76903346","https://openalex.org/I4210125590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019675860","display_name":"Paulo Menezes","orcid":"https://orcid.org/0000-0002-4903-3554"},"institutions":[{"id":"https://openalex.org/I76903346","display_name":"University of Coimbra","ror":"https://ror.org/04z8k9a98","country_code":"PT","type":"funder","lineage":["https://openalex.org/I76903346"]},{"id":"https://openalex.org/I4210125590","display_name":"Institute for Systems Engineering and Computers","ror":"https://ror.org/033wn8m60","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Paulo Menezes","raw_affiliation_strings":["Institute of Systems and Robotics, University of Coimbra, Coimbra, Portugal"],"affiliations":[{"raw_affiliation_string":"Institute of Systems and Robotics, University of Coimbra, Coimbra, Portugal","institution_ids":["https://openalex.org/I76903346","https://openalex.org/I4210125590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007787705","display_name":"Fernando Perdig\u00e3o","orcid":"https://orcid.org/0000-0002-8980-1992"},"institutions":[{"id":"https://openalex.org/I4210120471","display_name":"Instituto de Telecomunica\u00e7\u00f5es","ror":"https://ror.org/02ht4fk33","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210120471"]},{"id":"https://openalex.org/I76903346","display_name":"University of Coimbra","ror":"https://ror.org/04z8k9a98","country_code":"PT","type":"funder","lineage":["https://openalex.org/I76903346"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Fernando Perdigao","raw_affiliation_strings":["Instituto de Telecomunica\u00e7\u00f5es, University of Coimbra, Coimbra, Portugal"],"affiliations":[{"raw_affiliation_string":"Instituto de Telecomunica\u00e7\u00f5es, University of Coimbra, Coimbra, Portugal","institution_ids":["https://openalex.org/I4210120471","https://openalex.org/I76903346"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.29784,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":61,"max":69},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998,"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":0.9998,"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":0.9988,"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":0.997,"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/utterance","display_name":"Utterance","score":0.6636451},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.55693454},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.47728148}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6920346},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6636451},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6630897},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.56161094},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.55693454},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5157728},{"id":"https://openalex.org/C168862018","wikidata":"https://www.wikidata.org/wiki/Q5373805","display_name":"Emotionality","level":2,"score":0.50300044},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.47728148},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4606732},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3733306},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3355675},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3006389},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1547763},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/expat.2019.8876534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.4}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":6,"referenced_works":["https://openalex.org/W2032254851","https://openalex.org/W2399733683","https://openalex.org/W2589599921","https://openalex.org/W2594863811","https://openalex.org/W2726515241","https://openalex.org/W2911964244"],"related_works":["https://openalex.org/W4310979479","https://openalex.org/W4247736853","https://openalex.org/W2696990509","https://openalex.org/W2206035908","https://openalex.org/W2175373321","https://openalex.org/W2162158162","https://openalex.org/W2125642021","https://openalex.org/W1999004162","https://openalex.org/W1521049138","https://openalex.org/W1493012537"],"abstract_inverted_index":{"The":[0],"recognition":[1,130,147,173],"of":[2,22,36,41,73,138,174],"emotions":[3,92],"is":[4,62,114],"an":[5],"inherent":[6],"ability":[7],"possessed":[8],"by":[9,64],"humans,":[10],"which":[11,50],"has":[12,79],"long":[13],"intrigued":[14],"many":[15,58],"researchers.":[16],"Primarily":[17],"due":[18,55],"to":[19,44,56,80,89,168,184],"the":[20,87,98,136,139,156,188],"possibility":[21],"its":[23,57],"successful":[24],"emulation":[25],"and":[26,86,166],"integration":[27],"in":[28,93,116,187],"independent":[29],"systems.":[30],"Further,":[31],"speech,":[32,133],"being":[33],"a":[34,39,46,117,122,126],"mixture":[35],"utterances":[37,154],"conveying":[38],"state":[40],"mind,":[42],"proves":[43],"be":[45,53,103],"suitable":[47],"candidate":[48],"from":[49,132,155],"emotionality":[51,74,111],"can":[52],"inferred,":[54],"feature":[59,164],"variations.":[60],"This":[61],"corroborated":[63],"human":[65],"beings":[66],"themselves":[67],"using":[68],"this":[69],"modality":[70],"for":[71,106,162,171],"extraction":[72,165],"clues.":[75],"Another":[76],"important":[77],"aspect":[78],"do":[81],"with":[82,151],"communicational":[83],"register":[84],"adaptation":[85],"skill":[88],"discern":[90],"different":[91,94,108],"speakers.":[95],"Sure":[96],"enough,":[97],"same":[99],"emotional":[100,163,175],"utterance":[101],"may":[102],"interpreted":[104],"divergently":[105],"two":[107],"people,":[109],"meaning":[110],"specific":[112],"information":[113],"present":[115],"speaker's":[118],"personal":[119],"register.":[120],"As":[121],"demo,":[123],"we":[124],"propose":[125],"real-time":[127],"automatic":[128],"emotion":[129],"system":[131],"based":[134],"on":[135,159],"use":[137],"well":[140],"established":[141],"VGG-like":[142],"convolutional":[143],"neural":[144],"network":[145],"speaker":[146,160],"model":[148],"VGGVox,":[149],"trained":[150],"over":[152],"100,000":[153],"VoxCeleb1":[157],"dataset":[158],"recognition,":[161],"feeding":[167],"state-of-the-art":[169],"classifiers":[170],"accurate":[172],"states.":[176],"Positive":[177],"supporting":[178],"results":[179],"have":[180],"been":[181],"captivating":[182],"enough":[183],"spark":[185],"interest":[186],"technique.":[189]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2981664983","counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-02-18T23:17:39.800329","created_date":"2019-11-01"}