{"id":"https://openalex.org/W2995545690","doi":"https://doi.org/10.1109/aciiw.2019.8925044","title":"Exploring the Intersection Between Speaker Verification and Emotion Recognition","display_name":"Exploring the Intersection Between Speaker Verification and Emotion Recognition","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2995545690","doi":"https://doi.org/10.1109/aciiw.2019.8925044","mag":"2995545690"},"language":"en","primary_location":{"id":"doi:10.1109/aciiw.2019.8925044","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aciiw.2019.8925044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 8th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW)","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/A5031984850","display_name":"Michelle Bancroft","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michelle Bancroft","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Multimodal Signal Processing (MSP) laboratory, The University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Multimodal Signal Processing (MSP) laboratory, The University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041789037","display_name":"Reza Lotfian","orcid":"https://orcid.org/0000-0003-1891-0267"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Reza Lotfian","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Multimodal Signal Processing (MSP) laboratory, The University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Multimodal Signal Processing (MSP) laboratory, The University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Hansen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Multimodal Signal Processing (MSP) laboratory, The University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Multimodal Signal Processing (MSP) laboratory, The University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040793194","display_name":"Carlos Busso","orcid":"https://orcid.org/0000-0002-4075-4072"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carlos Busso","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Multimodal Signal Processing (MSP) laboratory, The University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Multimodal Signal Processing (MSP) laboratory, The University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"337","last_page":"342"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7983200550079346},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.636892557144165},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6280719637870789},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.592927873134613},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5200671553611755},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.44255346059799194},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4265727996826172},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.41321560740470886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3741118311882019}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7983200550079346},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.636892557144165},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6280719637870789},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.592927873134613},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5200671553611755},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.44255346059799194},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4265727996826172},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.41321560740470886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3741118311882019},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aciiw.2019.8925044","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aciiw.2019.8925044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 8th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W152668300","https://openalex.org/W189651667","https://openalex.org/W207824403","https://openalex.org/W1610857240","https://openalex.org/W1625928172","https://openalex.org/W2034007856","https://openalex.org/W2044401533","https://openalex.org/W2098742827","https://openalex.org/W2101587883","https://openalex.org/W2133167019","https://openalex.org/W2144005487","https://openalex.org/W2328138258","https://openalex.org/W2395750323","https://openalex.org/W2401417847","https://openalex.org/W2406312423","https://openalex.org/W2525412388","https://openalex.org/W2659927845","https://openalex.org/W2742542661","https://openalex.org/W2747172199","https://openalex.org/W2786667782","https://openalex.org/W2806649730","https://openalex.org/W2962839749","https://openalex.org/W2963447013","https://openalex.org/W6607727338","https://openalex.org/W6679622052","https://openalex.org/W6701903584","https://openalex.org/W6713727690"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"Many":[0],"scenarios":[1],"in":[2,62,126,152,192],"practical":[3],"applications":[4],"require":[5],"the":[6,35,51,72,87,127,145,171,176,181,187],"use":[7],"of":[8,24,53,66,89,109,118,147,170],"speaker":[9,38,91,193],"verification":[10,134],"systems":[11,95],"using":[12,157],"audio":[13],"with":[14],"high":[15],"emotional":[16,57,100,150,190],"content":[17,151],"(e.g.,":[18],"calls":[19],"from":[20,102,111,144],"911,":[21],"forensic":[22],"analysis":[23,84],"threatening":[25],"recordings).":[26],"For":[27],"these":[28,119,153,198],"cases,":[29],"it":[30],"is":[31,50],"important":[32],"to":[33,46,74,85,96,123,139,175],"explore":[34],"intersection":[36],"between":[37],"and":[39,64,79,92,179],"emotion":[40,93,159],"recognition":[41,94,160,194],"tasks.":[42],"A":[43],"key":[44],"challenge":[45],"address":[47],"this":[48,76],"problem":[49],"lack":[52],"resources,":[54],"since":[55],"current":[56],"databases":[58],"are":[59,137,155,200],"commonly":[60],"limited":[61],"size":[63],"number":[65],"speakers.":[67,104],"This":[68],"paper":[69],"(1)":[70],"creates":[71],"infrastructure":[73],"study":[75],"challenging":[77],"problems,":[78],"(2)":[80],"presents":[81],"an":[82],"exploratory":[83],"evaluate":[86],"accuracy":[88],"state-of-the-art":[90,158],"automatically":[97],"retrieve":[98,140],"specific":[99],"behaviors":[101],"target":[103,177,182],"We":[105],"collected":[106],"a":[107],"pool":[108,146],"sentences":[110,154,173],"multiple":[112],"speakers":[113,125,178],"(132,930":[114],"segments),":[115],"where":[116,168],"some":[117],"speaking":[120,133,142],"turns":[121,143],"belong":[122,174],"146":[124],"MSP-Podcast":[128],"database.":[129],"Our":[130],"framework":[131],"trains":[132],"models,":[135],"which":[136],"used":[138],"candidate":[141],"sentences.":[148],"The":[149,162,184],"detected":[156],"algorithms.":[161],"experimental":[163],"evaluation":[164],"provides":[165],"promising":[166],"results,":[167],"most":[169],"retrieved":[172],"has":[180],"emotion.":[183],"results":[185],"highlight":[186],"need":[188],"for":[189,202],"compensation":[191],"systems,":[195],"especially":[196],"if":[197],"models":[199],"intended":[201],"commercial":[203],"applications.":[204]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
