{"id":"https://openalex.org/W3015988193","doi":"https://doi.org/10.1109/icassp40776.2020.9054709","title":"Fusion Approaches for Emotion Recognition from Speech Using Acoustic and Text-Based Features","display_name":"Fusion Approaches for Emotion Recognition from Speech Using Acoustic and Text-Based Features","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015988193","doi":"https://doi.org/10.1109/icassp40776.2020.9054709","mag":"3015988193"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.18635","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077063899","display_name":"Leonardo Pepino","orcid":"https://orcid.org/0000-0001-5037-3700"},"institutions":[{"id":"https://openalex.org/I4210144290","display_name":"Institute of Astronomy and Space Physics","ror":"https://ror.org/03rq94151","country_code":"AR","type":"facility","lineage":["https://openalex.org/I151201029","https://openalex.org/I24354313","https://openalex.org/I4210123736","https://openalex.org/I4210144290","https://openalex.org/I4387155568"]},{"id":"https://openalex.org/I4210098917","display_name":"Instituto de Investigaciones en Ciencias de la Salud","ror":"https://ror.org/00vsnbn30","country_code":"AR","type":"facility","lineage":["https://openalex.org/I151201029","https://openalex.org/I166401450","https://openalex.org/I4210098917","https://openalex.org/I4210123736","https://openalex.org/I4210130626","https://openalex.org/I4387155568"]}],"countries":["AR"],"is_corresponding":true,"raw_author_name":"Leonardo Pepino","raw_affiliation_strings":["Instituto de Investigaci\u00f3n en Ciencias de la Computaci\u00f3n (ICC), CONICET-UBA, Argentina"],"affiliations":[{"raw_affiliation_string":"Instituto de Investigaci\u00f3n en Ciencias de la Computaci\u00f3n (ICC), CONICET-UBA, Argentina","institution_ids":["https://openalex.org/I4210098917","https://openalex.org/I4210144290"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004397011","display_name":"Pablo Riera","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098917","display_name":"Instituto de Investigaciones en Ciencias de la Salud","ror":"https://ror.org/00vsnbn30","country_code":"AR","type":"facility","lineage":["https://openalex.org/I151201029","https://openalex.org/I166401450","https://openalex.org/I4210098917","https://openalex.org/I4210123736","https://openalex.org/I4210130626","https://openalex.org/I4387155568"]},{"id":"https://openalex.org/I4210144290","display_name":"Institute of Astronomy and Space Physics","ror":"https://ror.org/03rq94151","country_code":"AR","type":"facility","lineage":["https://openalex.org/I151201029","https://openalex.org/I24354313","https://openalex.org/I4210123736","https://openalex.org/I4210144290","https://openalex.org/I4387155568"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Pablo Riera","raw_affiliation_strings":["Instituto de Investigaci\u00f3n en Ciencias de la Computaci\u00f3n (ICC), CONICET-UBA, Argentina"],"affiliations":[{"raw_affiliation_string":"Instituto de Investigaci\u00f3n en Ciencias de la Computaci\u00f3n (ICC), CONICET-UBA, Argentina","institution_ids":["https://openalex.org/I4210098917","https://openalex.org/I4210144290"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056267912","display_name":"Luciana Ferrer","orcid":"https://orcid.org/0000-0002-0426-8683"},"institutions":[{"id":"https://openalex.org/I4210144290","display_name":"Institute of Astronomy and Space Physics","ror":"https://ror.org/03rq94151","country_code":"AR","type":"facility","lineage":["https://openalex.org/I151201029","https://openalex.org/I24354313","https://openalex.org/I4210123736","https://openalex.org/I4210144290","https://openalex.org/I4387155568"]},{"id":"https://openalex.org/I4210098917","display_name":"Instituto de Investigaciones en Ciencias de la Salud","ror":"https://ror.org/00vsnbn30","country_code":"AR","type":"facility","lineage":["https://openalex.org/I151201029","https://openalex.org/I166401450","https://openalex.org/I4210098917","https://openalex.org/I4210123736","https://openalex.org/I4210130626","https://openalex.org/I4387155568"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Luciana Ferrer","raw_affiliation_strings":["Instituto de Investigaci\u00f3n en Ciencias de la Computaci\u00f3n (ICC), CONICET-UBA, Argentina"],"affiliations":[{"raw_affiliation_string":"Instituto de Investigaci\u00f3n en Ciencias de la Computaci\u00f3n (ICC), CONICET-UBA, Argentina","institution_ids":["https://openalex.org/I4210098917","https://openalex.org/I4210144290"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011425224","display_name":"Agust\u0131\u0301n Gravano","orcid":"https://orcid.org/0000-0003-2812-6361"},"institutions":[{"id":"https://openalex.org/I4210098917","display_name":"Instituto de Investigaciones en Ciencias de la Salud","ror":"https://ror.org/00vsnbn30","country_code":"AR","type":"facility","lineage":["https://openalex.org/I151201029","https://openalex.org/I166401450","https://openalex.org/I4210098917","https://openalex.org/I4210123736","https://openalex.org/I4210130626","https://openalex.org/I4387155568"]},{"id":"https://openalex.org/I4210144290","display_name":"Institute of Astronomy and Space Physics","ror":"https://ror.org/03rq94151","country_code":"AR","type":"facility","lineage":["https://openalex.org/I151201029","https://openalex.org/I24354313","https://openalex.org/I4210123736","https://openalex.org/I4210144290","https://openalex.org/I4387155568"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Agustin Gravano","raw_affiliation_strings":["Instituto de Investigaci\u00f3n en Ciencias de la Computaci\u00f3n (ICC), CONICET-UBA, Argentina"],"affiliations":[{"raw_affiliation_string":"Instituto de Investigaci\u00f3n en Ciencias de la Computaci\u00f3n (ICC), CONICET-UBA, Argentina","institution_ids":["https://openalex.org/I4210098917","https://openalex.org/I4210144290"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5077063899"],"corresponding_institution_ids":["https://openalex.org/I4210098917","https://openalex.org/I4210144290"],"apc_list":null,"apc_paid":null,"fwci":5.4857,"has_fulltext":true,"cited_by_count":53,"citation_normalized_percentile":{"value":0.96800366,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6484","last_page":"6488"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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":0.9991000294685364,"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/computer-science","display_name":"Computer science","score":0.8065599799156189},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6299102306365967},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.581290066242218},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5409266948699951},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48825860023498535},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.48565781116485596},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4687274694442749},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46031591296195984},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4441981613636017},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.41334232687950134},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.28174129128456116},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06832575798034668}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8065599799156189},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6299102306365967},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.581290066242218},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5409266948699951},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48825860023498535},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.48565781116485596},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4687274694442749},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46031591296195984},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4441981613636017},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.41334232687950134},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28174129128456116},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06832575798034668},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2403.18635","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.18635","pdf_url":"https://arxiv.org/pdf/2403.18635","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2403.18635","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.18635","pdf_url":"https://arxiv.org/pdf/2403.18635","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3015988193.pdf"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W1534131679","https://openalex.org/W2058787788","https://openalex.org/W2080576537","https://openalex.org/W2085662862","https://openalex.org/W2135256083","https://openalex.org/W2140801466","https://openalex.org/W2146334809","https://openalex.org/W2181741066","https://openalex.org/W2250539671","https://openalex.org/W2602034649","https://openalex.org/W2696559478","https://openalex.org/W2742542661","https://openalex.org/W2747664154","https://openalex.org/W2896457183","https://openalex.org/W2916113431","https://openalex.org/W2937833637","https://openalex.org/W2962770129","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2964121744","https://openalex.org/W2972463723","https://openalex.org/W2972493869","https://openalex.org/W2972921424","https://openalex.org/W2973034847","https://openalex.org/W2973110385","https://openalex.org/W2983159143","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6679992976","https://openalex.org/W6739901393","https://openalex.org/W6742848714","https://openalex.org/W6755207826"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2097963413","https://openalex.org/W2294335174","https://openalex.org/W2185469136","https://openalex.org/W2025614924","https://openalex.org/W3145575561","https://openalex.org/W2121652828","https://openalex.org/W4388820305","https://openalex.org/W4221161909"],"abstract_inverted_index":{"In":[0,111],"this":[1,37,120],"paper,":[2],"we":[3,94],"study":[4],"different":[5,51],"approaches":[6],"for":[7,92,119,130],"classifying":[8],"emotions":[9],"from":[10],"speech":[11,32],"using":[12,43],"acoustic":[13,71],"and":[14,34,49,57,64,72],"text-based":[15,73,132],"features.":[16],"We":[17,46,67],"propose":[18,48],"to":[19,26,53,103],"obtain":[20],"contextualized":[21],"word":[22],"embeddings":[23],"with":[24],"BERT":[25],"represent":[27],"the":[28,55,87,96,100,105,113,131,141],"information":[29],"contained":[30],"in":[31,39,123],"transcriptions":[33],"show":[35,95],"that":[36,69,99,135],"results":[38,122],"better":[40],"performance":[41,129],"than":[42],"Glove":[44],"embeddings.":[45],"also":[47],"compare":[50],"strategies":[52],"combine":[54],"audio":[56],"text":[58],"modalities,":[59],"evaluating":[60],"them":[61],"on":[62,77,109],"IEMOCAP":[63],"MSPPODCAST":[65],"datasets.":[66],"find":[68],"fusing":[70],"systems":[74],"is":[75],"beneficial":[76],"both":[78],"datasets,":[79],"though":[80],"only":[81],"subtle":[82],"differences":[83],"are":[84],"observed":[85],"across":[86],"evaluated":[88],"fusion":[89],"approaches.":[90],"Finally,":[91],"IEMOCAP,":[93],"large":[97],"effect":[98],"criteria":[101],"used":[102],"define":[104],"cross-validation":[106],"folds":[107,118],"have":[108],"results.":[110],"particular,":[112],"standard":[114],"way":[115],"of":[116,128,143],"creating":[117],"dataset":[121],"a":[124],"highly":[125],"optimistic":[126],"estimation":[127],"system,":[133],"suggesting":[134],"some":[136],"previous":[137],"works":[138],"may":[139],"overestimate":[140],"advantage":[142],"incorporating":[144],"transcriptions.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2020-04-17T00:00:00"}
