{"id":"https://openalex.org/W2143657265","doi":"https://doi.org/10.1109/tasl.2009.2034187","title":"Comparison of Speaker Adaptation Methods as Feature Extraction for SVM-Based Speaker Recognition","display_name":"Comparison of Speaker Adaptation Methods as Feature Extraction for SVM-Based Speaker Recognition","publication_year":2009,"publication_date":"2009-10-09","ids":{"openalex":"https://openalex.org/W2143657265","doi":"https://doi.org/10.1109/tasl.2009.2034187","mag":"2143657265"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2009.2034187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2009.2034187","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-01690338v1/file/taslp_ferras_2010.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027284390","display_name":"Marc Ferr\u00e0s","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"M Ferras","raw_affiliation_strings":["LIMSI-CNRS, Orsay, France","LIMSI CNRS, Orsay, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIMSI-CNRS, Orsay, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210115485"]},{"raw_affiliation_string":"LIMSI CNRS, Orsay, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210115485"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113828649","display_name":"Cheung-Chi Leung","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Cheung-Chi Leung","raw_affiliation_strings":["Human Language Technology Department, Institute for Infocomm Research, Singapore","Human Language Technology Department, Institute for Infocomm Research (I2R), Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Department, Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Human Language Technology Department, Institute for Infocomm Research (I2R), Singapore, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111156181","display_name":"C. Barras","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"C Barras","raw_affiliation_strings":["LIMSI-CNRS, Orsay, France","LIMSI CNRS, Orsay, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIMSI-CNRS, Orsay, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210115485"]},{"raw_affiliation_string":"LIMSI CNRS, Orsay, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210115485"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109050158","display_name":"J.-L. Gauvain","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"J.-L. Gauvain","raw_affiliation_strings":["LIMSI-CNRS, Orsay, France","LIMSI CNRS, Orsay, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIMSI-CNRS, Orsay, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210115485"]},{"raw_affiliation_string":"LIMSI CNRS, Orsay, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210115485"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6169,"has_fulltext":true,"cited_by_count":36,"citation_normalized_percentile":{"value":0.91399824,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"18","issue":"6","first_page":"1366","last_page":"1378"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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":0.9973999857902527,"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/T11309","display_name":"Music and Audio Processing","score":0.9855999946594238,"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/support-vector-machine","display_name":"Support vector machine","score":0.7592052221298218},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7024453282356262},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6638506650924683},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6425671577453613},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6147956252098083},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5838974714279175},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5503895282745361},{"id":"https://openalex.org/keywords/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.46698421239852905},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.4424440562725067},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.44129323959350586},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.19950562715530396},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10397714376449585},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06841173768043518}],"concepts":[{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.7592052221298218},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7024453282356262},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6638506650924683},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6425671577453613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6147956252098083},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5838974714279175},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5503895282745361},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.46698421239852905},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.4424440562725067},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.44129323959350586},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.19950562715530396},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10397714376449585},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06841173768043518}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tasl.2009.2034187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2009.2034187","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-01690338v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01690338","pdf_url":"https://hal.science/hal-01690338v1/file/taslp_ferras_2010.pdf","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Audio, Speech and Language Processing, 2010, 18 (6), pp.1366 - 1378. &#x27E8;10.1109/TASL.2009.2034187&#x27E9;","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01690338v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01690338","pdf_url":"https://hal.science/hal-01690338v1/file/taslp_ferras_2010.pdf","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Audio, Speech and Language Processing, 2010, 18 (6), pp.1366 - 1378. &#x27E8;10.1109/TASL.2009.2034187&#x27E9;","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2143657265.pdf","grobid_xml":"https://content.openalex.org/works/W2143657265.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W17749540","https://openalex.org/W32979931","https://openalex.org/W1553271421","https://openalex.org/W1586405805","https://openalex.org/W1599512239","https://openalex.org/W1604938182","https://openalex.org/W1741269295","https://openalex.org/W2037740282","https://openalex.org/W2041823554","https://openalex.org/W2078953162","https://openalex.org/W2097470427","https://openalex.org/W2100969003","https://openalex.org/W2105393821","https://openalex.org/W2105667909","https://openalex.org/W2107638917","https://openalex.org/W2121981798","https://openalex.org/W2133233779","https://openalex.org/W2139212933","https://openalex.org/W2141279928","https://openalex.org/W2144760012","https://openalex.org/W2146871184","https://openalex.org/W2147147599","https://openalex.org/W2162471146","https://openalex.org/W2168561756","https://openalex.org/W2397634864","https://openalex.org/W2405891901","https://openalex.org/W2406690299","https://openalex.org/W2407231000","https://openalex.org/W3002694247","https://openalex.org/W3145606929","https://openalex.org/W3193477162","https://openalex.org/W6600721324","https://openalex.org/W6601396385","https://openalex.org/W6633168720","https://openalex.org/W6713760821","https://openalex.org/W6714085554","https://openalex.org/W6714201320"],"related_works":["https://openalex.org/W2118039276","https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162"],"abstract_inverted_index":{"In":[0,98],"the":[1,4,62,85,93,107,116,128,138,147,163,171,185,194],"last":[2],"years":[3],"speaker":[5,13,18,71,156,164],"recognition":[6,72],"field":[7],"has":[8],"made":[9],"extensive":[10],"use":[11,79],"of":[12,66,106,127],"adaptation":[14,57],"techniques.":[15],"Adaptation":[16],"allows":[17],"model":[19],"parameters":[20,90],"to":[21,76,82,136,141,143,160],"be":[22],"estimated":[23],"using":[24,155,193],"less":[25],"speech":[26,148],"data":[27,180],"than":[28],"needed":[29],"for":[30,51],"maximum-likelihood":[31,42],"(ML)":[32],"training.":[33],"The":[34,189],"maximum":[35],"<i":[36],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[37],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">a":[38],"posteriori</i>":[39],"(MAP)":[40],"and":[41,55,109,121,124,174,181,199],"linear":[43],"regression":[44,201],"(MLLR)":[45],"techniques":[46],"have":[47,58],"typically":[48],"been":[49,59],"used":[50,135],"adaptation.":[52],"Recently,":[53],"MAP":[54],"MLLR":[56,94,139,165],"incorporated":[60],"in":[61,146],"feature":[63,77],"extraction":[64,78],"stage":[65],"support":[67],"vector":[68,89],"machine":[69],"(SVM)-based":[70],"systems.":[73],"Two":[74],"approaches":[75],"a":[80],"SVM":[81],"classify":[83],"either":[84],"MAP-adapted":[86],"Gaussian":[87],"mean":[88],"(GSV-SVM)":[91],"or":[92],"transform":[95],"coefficients":[96],"(MLLR-SVM).":[97],"this":[99],"paper,":[100],"we":[101],"provide":[102,168],"an":[103],"experimental":[104],"analysis":[105],"GSV-SVM":[108],"MLLR-SVM":[110],"approaches.":[111],"We":[112,167],"largely":[113],"focus":[114],"on":[115,170,184],"latter":[117],"by":[118],"exploring":[119],"constrained":[120],"unconstrained":[122],"transforms":[123,140],"different":[125],"choices":[126],"acoustic":[129,151],"model.":[130],"A":[131],"channel-compensated":[132],"front-end":[133],"is":[134],"prevent":[137],"adapt":[142],"channel":[144],"components":[145],"data.":[149,188],"Additional":[150],"models":[152,198],"were":[153],"trained":[154],"adaptive":[157],"training":[158],"(SAT)":[159],"better":[161],"estimate":[162],"transforms.":[166],"results":[169,183,190],"NIST":[172],"2005":[173],"2006":[175,187],"Speaker":[176],"Recognition":[177],"Evaluation":[178],"(SRE)":[179],"fusion":[182],"SRE":[186],"show":[191],"that":[192],"compensated":[195],"front-end,":[196],"SAT":[197],"multiple":[200],"classes":[202],"bring":[203],"major":[204],"performance":[205],"improvements.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}