{"id":"https://openalex.org/W1983424905","doi":"https://doi.org/10.1109/apsipa.2013.6694123","title":"Emotional adaptive training for speaker verification","display_name":"Emotional adaptive training for speaker verification","publication_year":2013,"publication_date":"2013-10-01","ids":{"openalex":"https://openalex.org/W1983424905","doi":"https://doi.org/10.1109/apsipa.2013.6694123","mag":"1983424905"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2013.6694123","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2013.6694123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference","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/A5002013485","display_name":"Fanhu Bie","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fanhu Bie","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University, China","Center for Speech & Language Technol., Tsinghua Univ., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Center for Speech & Language Technol., Tsinghua Univ., Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391494","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-6992-7950"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University, China","Center for Speech & Language Technol., Tsinghua Univ., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Center for Speech & Language Technol., Tsinghua Univ., Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084318285","display_name":"Thomas Fang Zheng","orcid":"https://orcid.org/0000-0002-0249-4767"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Thomas Fang Zheng","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University, China","Center for Speech & Language Technol., Tsinghua Univ., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Center for Speech & Language Technol., Tsinghua Univ., Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047221036","display_name":"Javier Tejedor","orcid":"https://orcid.org/0000-0001-7699-5620"},"institutions":[{"id":"https://openalex.org/I63634437","display_name":"Universidad Aut\u00f3noma de Madrid","ror":"https://ror.org/01cby8j38","country_code":"ES","type":"education","lineage":["https://openalex.org/I63634437"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Javier Tejedor","raw_affiliation_strings":["Human Computer Technology Laboratory, Universidad Aut\u00f3noma de Madrid, Spain","Human Comput. Technol. Lab., Univ. Autonoma de Madrid, Cantoblanco, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Computer Technology Laboratory, Universidad Aut\u00f3noma de Madrid, Spain","institution_ids":["https://openalex.org/I63634437"]},{"raw_affiliation_string":"Human Comput. Technol. Lab., Univ. Autonoma de Madrid, Cantoblanco, Spain","institution_ids":["https://openalex.org/I63634437"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081135618","display_name":"Ruxin Chen","orcid":"https://orcid.org/0009-0000-0624-4127"},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruxin Chen","raw_affiliation_strings":["R&D, Sony Computer Entertainment America, Foster City, CA, USA","R&D, Sony Comput. Entertainment America, Foster City, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"R&D, Sony Computer Entertainment America, Foster City, CA, USA","institution_ids":["https://openalex.org/I2800278093"]},{"raw_affiliation_string":"R&D, Sony Comput. Entertainment America, Foster City, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"3784","issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9961000084877014,"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/T11309","display_name":"Music and Audio Processing","score":0.9948999881744385,"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-recognition","display_name":"Speech recognition","score":0.7427945137023926},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7375088930130005},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.512120246887207},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.49933409690856934},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4610845446586609},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4462529122829437},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4379289150238037},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.41755765676498413},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4101221561431885},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37021052837371826},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33742183446884155},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.21191444993019104}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7427945137023926},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7375088930130005},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.512120246887207},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.49933409690856934},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4610845446586609},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4462529122829437},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4379289150238037},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.41755765676498413},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4101221561431885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37021052837371826},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33742183446884155},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.21191444993019104},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/apsipa.2013.6694123","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2013.6694123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:repositorio.uam.es:10486/666433","is_oa":false,"landing_page_url":"http://hdl.handle.net/10486/666433","pdf_url":null,"source":{"id":"https://openalex.org/S4306400964","display_name":"Biblos-e Archivo (Universidad Aut\u00f3noma de Madrid)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63634437","host_organization_name":"Universidad Aut\u00f3noma de Madrid","host_organization_lineage":["https://openalex.org/I63634437"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"conferenceObject"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.719.3318","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.719.3318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cslt.riit.tsinghua.edu.cn/%7Efzheng/PAPERS/2013/1310E_APSIPA_Emotional-adaptive-training4SV_BFH%28ZF%29.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.75,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1828425977","display_name":null,"funder_award_id":"973 Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G465702083","display_name":null,"funder_award_id":"2013CB329302","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8204283577","display_name":"\u8bf4\u8bdd\u4eba\u8bc6\u522b\u4e2d\u65f6\u53d8\u9c81\u68d2\u7684\u58f0\u7eb9\u7279\u5f81\u7814\u7a76","funder_award_id":"61271389","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W9537764","https://openalex.org/W108572996","https://openalex.org/W131138742","https://openalex.org/W189651667","https://openalex.org/W1480229134","https://openalex.org/W1557292420","https://openalex.org/W1599512239","https://openalex.org/W1747744034","https://openalex.org/W2024636541","https://openalex.org/W2037740282","https://openalex.org/W2041823554","https://openalex.org/W2069631319","https://openalex.org/W2119468495","https://openalex.org/W2141807049","https://openalex.org/W2146871184","https://openalex.org/W2224914820","https://openalex.org/W6600385197","https://openalex.org/W6604472697","https://openalex.org/W6605360261","https://openalex.org/W6607727338","https://openalex.org/W6628765830","https://openalex.org/W6633322633","https://openalex.org/W6637637785","https://openalex.org/W6680931295","https://openalex.org/W6689225245"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"Speaker":[0],"verification":[1,31],"suffers":[2],"from":[3],"significant":[4,27,119,156],"performance":[5,28,120],"degradation":[6],"with":[7,61,168],"emotion":[8],"variation.":[9],"In":[10],"a":[11,26,76,155],"previous":[12],"study,":[13],"we":[14],"have":[15],"demonstrated":[16],"that":[17,114],"an":[18,42,97],"adaptation":[19],"approach":[20,49,117,161,187],"based":[21,206],"on":[22,32,96,207],"MLLR/CMLLR":[23],"can":[24,67],"provide":[25],"improvement":[29],"for":[30],"emotional":[33,43,71,98,140,175,190,202],"speech.":[34],"This":[35,48,80],"paper":[36],"follows":[37],"this":[38],"direction":[39],"and":[40,56,138,173,200],"presents":[41],"adaptive":[44,86],"training":[45,87],"(EAT)":[46],"approach.":[47],"iteratively":[50],"estimates":[51],"the":[52,58,62,84,115,123,127,135,139,159,163,169,174,185,189,201,208],"emotion-dependent":[53,197],"CMLLR":[54,181],"transformations":[55],"re-trains":[57],"speaker":[59,78,85,136,164,198],"models":[60,137,165,199],"transformed":[63,179],"speech,":[64],"which":[65,101],"therefore":[66],"make":[68],"use":[69],"of":[70,105],"enrollment":[72,129,171,191],"speech":[73,90,99,103,172],"to":[74,83,133,195],"train":[75,134,196],"stronger":[77],"model.":[79],"is":[81],"similar":[82],"(SAT)":[88],"in":[89,108,154,182],"recognition.":[91],"The":[92,111,146],"experiments":[93],"are":[94,131,143,166,178,193,204],"conducted":[95],"database":[100],"involves":[102],"recordings":[104],"30":[106],"speakers":[107],"5":[109],"emotions.":[110],"results":[112],"demonstrate":[113],"EAT":[116,147],"provides":[118],"improvements":[121],"over":[122],"baseline":[124],"system":[125],"where":[126,162,188],"neutral":[128,170],"data":[130,192],"used":[132,194],"test":[141,176],"utterances":[142,177,203],"verified":[144,205],"directly.":[145],"also":[148],"outperforms":[149],"another":[150],"two":[151],"emotionadaptation":[152],"approaches":[153],"way:":[157],"(1)":[158],"CMLLR-based":[160],"trained":[167],"by":[180],"verification;":[183],"(2)":[184],"MAP-based":[186],"emotion-matched":[209],"models.":[210]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
