{"id":"https://openalex.org/W2403238720","doi":"https://doi.org/10.1109/icassp.2016.7472651","title":"Domain adaptation using maximum likelihood linear transformation for PLDA-based speaker verification","display_name":"Domain adaptation using maximum likelihood linear transformation for PLDA-based speaker verification","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2403238720","doi":"https://doi.org/10.1109/icassp.2016.7472651","mag":"2403238720"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5101991100","display_name":"Qiongqiong Wang","orcid":"https://orcid.org/0000-0002-9903-0618"},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Qiongqiong Wang","raw_affiliation_strings":["NEC Corporation, Information and Media Processing Laboratories"],"affiliations":[{"raw_affiliation_string":"NEC Corporation, Information and Media Processing Laboratories","institution_ids":["https://openalex.org/I118347220"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059740393","display_name":"H. Yamamoto","orcid":"https://orcid.org/0000-0001-7966-2629"},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hitoshi Yamamoto","raw_affiliation_strings":["NEC Corporation, Information and Media Processing Laboratories"],"affiliations":[{"raw_affiliation_string":"NEC Corporation, Information and Media Processing Laboratories","institution_ids":["https://openalex.org/I118347220"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031109112","display_name":"Takafumi Koshinaka","orcid":"https://orcid.org/0000-0002-2343-5125"},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takafumi Koshinaka","raw_affiliation_strings":["NEC Corporation, Information and Media Processing Laboratories"],"affiliations":[{"raw_affiliation_string":"NEC Corporation, Information and Media Processing Laboratories","institution_ids":["https://openalex.org/I118347220"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101991100"],"corresponding_institution_ids":["https://openalex.org/I118347220"],"apc_list":null,"apc_paid":null,"fwci":3.8563,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.94179615,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"8","issue":null,"first_page":"5110","last_page":"5114"},"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":0.9977999925613403,"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":0.9936000108718872,"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":0.811214804649353},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.6960172653198242},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.6776692271232605},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.622306227684021},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.6133688688278198},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5836219787597656},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5787383913993835},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5300918221473694},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4905788004398346},{"id":"https://openalex.org/keywords/linear-map","display_name":"Linear map","score":0.43376362323760986},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.42669016122817993},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.41720306873321533},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11197203397750854},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08158159255981445}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.811214804649353},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.6960172653198242},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.6776692271232605},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.622306227684021},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.6133688688278198},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5836219787597656},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5787383913993835},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5300918221473694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4905788004398346},{"id":"https://openalex.org/C49766605","wikidata":"https://www.wikidata.org/wiki/Q207643","display_name":"Linear map","level":2,"score":0.43376362323760986},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.42669016122817993},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.41720306873321533},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11197203397750854},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08158159255981445},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":23,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W854558135","https://openalex.org/W1524333225","https://openalex.org/W1589137271","https://openalex.org/W1999033484","https://openalex.org/W2004497042","https://openalex.org/W2043273367","https://openalex.org/W2046015436","https://openalex.org/W2067301010","https://openalex.org/W2073017590","https://openalex.org/W2101261946","https://openalex.org/W2150769028","https://openalex.org/W2181594395","https://openalex.org/W2294814385","https://openalex.org/W2360384684","https://openalex.org/W2401594978","https://openalex.org/W2406312423","https://openalex.org/W6603931906","https://openalex.org/W6623801645","https://openalex.org/W6631362777","https://openalex.org/W6635152626","https://openalex.org/W6696784865","https://openalex.org/W6713727690"],"related_works":["https://openalex.org/W2038416447","https://openalex.org/W2364151838","https://openalex.org/W2066926363","https://openalex.org/W1623358412","https://openalex.org/W2354159744","https://openalex.org/W2351539857","https://openalex.org/W2016659636","https://openalex.org/W2016291788","https://openalex.org/W2188166326","https://openalex.org/W1989668101"],"abstract_inverted_index":{"While":[0],"i-vector-PLDA":[1],"frameworks":[2],"employing":[3],"huge":[4],"amounts":[5,55],"of":[6,25,41,56,83,101],"development":[7],"data":[8,26,52],"have":[9],"achieved":[10,114],"significant":[11],"success":[12],"in":[13,43,72,104],"speaker":[14,45],"recognition,":[15],"it":[16,122],"is":[17,92],"infeasible":[18],"to":[19,36,94],"collect":[20],"a":[21,34,118,124],"sufficiently":[22],"large":[23],"amount":[24],"for":[27],"every":[28],"real":[29],"application.":[30],"This":[31],"paper":[32],"proposes":[33],"method":[35,109,126],"perform":[37],"supervised":[38],"domain":[39,74,80],"adaptation":[40],"PLDA":[42],"i-vector-based":[44],"recognition":[46],"systems":[47],"with":[48],"available":[49],"resource-rich":[50],"mismatched":[51],"and":[53,64],"small":[54],"matched":[57],"data,":[58],"under":[59],"two":[60,102],"assumptions:":[61],"(1)":[62],"between-speaker":[63],"within-speaker":[65],"covariances":[66],"depend":[67],"on":[68,128],"domains;":[69],"(2)":[70],"features":[71],"one":[73],"can":[75],"be":[76],"transformed":[77],"into":[78],"another":[79],"by":[81],"means":[82],"an":[84],"affine":[85],"transformation.":[86],"Maximum":[87],"likelihood":[88],"linear":[89,129],"transformation":[90],"(MLLT)":[91],"used":[93],"infer":[95],"the":[96,99],"relationship":[97],"between":[98],"datasets":[100],"domains":[103],"training":[105],"PLDA.":[106],"The":[107],"proposed":[108],"improves":[110],"performance":[111],"over":[112],"that":[113],"without":[115],"adaptation.":[116],"Using":[117],"score":[119],"fusion":[120],"technique,":[121],"outperforms":[123],"conventional":[125],"based":[127],"combination.":[130]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}