{"id":"https://openalex.org/W2745733005","doi":"https://doi.org/10.21437/interspeech.2017-668","title":"Domain Mismatch Modeling of Out-Domain i-Vectors for PLDA Speaker Verification","display_name":"Domain Mismatch Modeling of Out-Domain i-Vectors for PLDA Speaker Verification","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2745733005","doi":"https://doi.org/10.21437/interspeech.2017-668","mag":"2745733005"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-668","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.qut.edu.au/110426/16/template-2.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100776664","display_name":"Md Hafizur Rahman","orcid":"https://orcid.org/0000-0001-6576-1554"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Md. Hafizur Rahman","raw_affiliation_strings":["Speech and Audio Research Laboratory, Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Speech and Audio Research Laboratory, Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039529498","display_name":"Ivan Himawan","orcid":"https://orcid.org/0000-0003-3848-244X"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ivan Himawan","raw_affiliation_strings":["Speech and Audio Research Laboratory, Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Speech and Audio Research Laboratory, Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000014182","display_name":"David Dean","orcid":"https://orcid.org/0000-0003-1274-9775"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"David Dean","raw_affiliation_strings":["Speech and Audio Research Laboratory, Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Speech and Audio Research Laboratory, Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055128383","display_name":"Sridha Sridharan","orcid":"https://orcid.org/0000-0003-4316-9001"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sridha Sridharan","raw_affiliation_strings":["Speech and Audio Research Laboratory, Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Speech and Audio Research Laboratory, Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100776664"],"corresponding_institution_ids":["https://openalex.org/I160993911"],"apc_list":null,"apc_paid":null,"fwci":1.0382,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.83273151,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1581","last_page":"1585"},"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/T10860","display_name":"Speech and Audio Processing","score":0.996399998664856,"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":0.9869999885559082,"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":0.7956621050834656},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7173942923545837},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.6334633827209473},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5779867172241211},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5756502151489258},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5408059358596802},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5066397786140442},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.4481203556060791},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3244379162788391},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1436203420162201},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07667174935340881}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7956621050834656},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7173942923545837},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.6334633827209473},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5779867172241211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5756502151489258},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5408059358596802},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5066397786140442},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.4481203556060791},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3244379162788391},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1436203420162201},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07667174935340881},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2017-668","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.qut.edu.au:110426","is_oa":true,"landing_page_url":"http://www.isca-speech.org/archive/Interspeech_2017/","pdf_url":"https://eprints.qut.edu.au/110426/16/template-2.pdf","source":{"id":"https://openalex.org/S4306402607","display_name":"QUT ePrints (Queensland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I160993911","host_organization_name":"Queensland University of Technology","host_organization_lineage":["https://openalex.org/I160993911"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 18th Annual Conference of the International Speech Communication Association (INTERSPEECH 2017)","raw_type":"Chapter in Book, Report or Conference volume"}],"best_oa_location":{"id":"pmh:oai:eprints.qut.edu.au:110426","is_oa":true,"landing_page_url":"http://www.isca-speech.org/archive/Interspeech_2017/","pdf_url":"https://eprints.qut.edu.au/110426/16/template-2.pdf","source":{"id":"https://openalex.org/S4306402607","display_name":"QUT ePrints (Queensland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I160993911","host_organization_name":"Queensland University of Technology","host_organization_lineage":["https://openalex.org/I160993911"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 18th Annual Conference of the International Speech Communication Association (INTERSPEECH 2017)","raw_type":"Chapter in Book, Report or Conference volume"},"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2745733005.pdf"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W117978701","https://openalex.org/W866349134","https://openalex.org/W1480629789","https://openalex.org/W1505813640","https://openalex.org/W1999033484","https://openalex.org/W2004497042","https://openalex.org/W2046015436","https://openalex.org/W2067301010","https://openalex.org/W2073017590","https://openalex.org/W2150769028","https://openalex.org/W2360384684","https://openalex.org/W2394709239","https://openalex.org/W2395750323","https://openalex.org/W2403238720","https://openalex.org/W2403367729","https://openalex.org/W2403589179","https://openalex.org/W2406312423"],"related_works":["https://openalex.org/W1968216131","https://openalex.org/W2355011896","https://openalex.org/W3089964815","https://openalex.org/W1581134722","https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W2169890399","https://openalex.org/W2170952763","https://openalex.org/W2359348847","https://openalex.org/W4235705411"],"abstract_inverted_index":{"The":[0,128],"state-of-the-art":[1],"i-vector":[2],"based":[3],"probabilistic":[4],"linear":[5],"discriminant":[6],"analysis":[7],"(PLDA)":[8],"trained":[9],"on":[10],"non-target":[11],"(or":[12],"out-":[13],"domain)":[14],"data":[15,45],"significantly":[16],"affects":[17],"the":[18,24,34,51,75,79,90],"speaker":[19,35,109],"verification":[20,36],"performance":[21],"due":[22],"to":[23,49,71,134],"domain":[25,41,61,76],"mismatch":[26,42,62],"between":[27],"training":[28,81],"and":[29,73],"evaluation":[30],"data.":[31],"To":[32],"improve":[33],"performance,":[37],"sufficient":[38],"amount":[39],"of":[40,115],"compensated":[43],"out-domain":[44,80,104],"must":[46],"be":[47],"used":[48],"train":[50],"PLDA":[52,139],"models":[53],"successfully.":[54],"In":[55],"this":[56],"paper,":[57],"we":[58,87],"propose":[59],"a":[60,97],"model-":[63],"ing":[64],"(DMM)":[65],"technique":[66,92,131],"using":[67],"maximum-a-posteriori":[68],"(MAP)":[69],"estimation":[70],"model":[72],"compensate":[74],"variability":[77],"from":[78],"i-vectors.":[82,149],"From":[83],"our":[84],"experimental":[85],"results,":[86],"found":[88],"that":[89],"DMM":[91,121],"can":[93],"achieve":[94],"at":[95],"least":[96],"24%":[98],"improvement":[99,114],"in":[100],"EER":[101],"over":[102],"an":[103],"only":[105,142],"base-":[106],"line":[107],"when":[108,119],"labels":[110],"are":[111],"available.":[112],"Further":[113],"3%":[116],"is":[117,132],"obtained":[118],"combining":[120],"with":[122,141],"domain-invariant":[123],"covariance":[124],"normalization":[125],"(DICN)":[126],"approach.":[127],"DMM/DICN":[129],"combined":[130],"shown":[133],"perform":[135],"better":[136],"than":[137],"in-domain":[138],"system":[140],"200":[143],"labeled":[144],"speakers":[145],"or":[146],"2,000":[147],"unlabeled":[148]},"counts_by_year":[{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}