{"id":"https://openalex.org/W2604209903","doi":"https://doi.org/10.1109/taslp.2017.2692304","title":"DNN-Driven Mixture of PLDA for Robust Speaker Verification","display_name":"DNN-Driven Mixture of PLDA for Robust Speaker Verification","publication_year":2017,"publication_date":"2017-04-07","ids":{"openalex":"https://openalex.org/W2604209903","doi":"https://doi.org/10.1109/taslp.2017.2692304","mag":"2604209903"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2017.2692304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2692304","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM 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":"http://ira.lib.polyu.edu.hk/bitstream/10397/70611/1/Mak_Dnn-Driven_Mixture_Plda.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100368199","display_name":"Na Li","orcid":"https://orcid.org/0000-0003-2669-0233"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Na Li","raw_affiliation_strings":["Department of Electronic and Information Engineering, Hong Kong Polytechnic University, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic and Information Engineering, Hong Kong Polytechnic University, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068768998","display_name":"Man\u2010Wai Mak","orcid":"https://orcid.org/0000-0001-8854-3760"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Man-Wai Mak","raw_affiliation_strings":["Department of Electronic and Information Engineering, Hong Kong Polytechnic University, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic and Information Engineering, Hong Kong Polytechnic University, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061908942","display_name":"Jen\u2010Tzung Chien","orcid":"https://orcid.org/0000-0003-3466-8941"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Tzung Chien","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9907,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.92968256,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"25","issue":"6","first_page":"1371","last_page":"1383"},"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":0.9986000061035156,"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":0.9879000186920166,"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":0.7410336136817932},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7124078273773193},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6615256071090698},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.53956139087677},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5246051549911499},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4919097423553467},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4908803105354309},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.490181028842926},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.48578718304634094},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4778853952884674},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.45791923999786377},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.4562673270702362},{"id":"https://openalex.org/keywords/likelihood-ratio-test","display_name":"Likelihood-ratio test","score":0.45393383502960205},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3869539201259613},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.309529572725296},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17269060015678406},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12908610701560974}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7410336136817932},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7124078273773193},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6615256071090698},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.53956139087677},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5246051549911499},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4919097423553467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4908803105354309},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.490181028842926},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.48578718304634094},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4778853952884674},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.45791923999786377},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.4562673270702362},{"id":"https://openalex.org/C9483764","wikidata":"https://www.wikidata.org/wiki/Q585740","display_name":"Likelihood-ratio test","level":2,"score":0.45393383502960205},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3869539201259613},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.309529572725296},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17269060015678406},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12908610701560974},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2017.2692304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2692304","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/70611","is_oa":true,"landing_page_url":"http://hdl.handle.net/10397/70611","pdf_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/70611/1/Mak_Dnn-Driven_Mixture_Plda.pdf","source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal/Magazine Article"}],"best_oa_location":{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/70611","is_oa":true,"landing_page_url":"http://hdl.handle.net/10397/70611","pdf_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/70611/1/Mak_Dnn-Driven_Mixture_Plda.pdf","source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal/Magazine Article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.75,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2604209903.pdf"},"referenced_works_count":67,"referenced_works":["https://openalex.org/W111477576","https://openalex.org/W128628490","https://openalex.org/W620149980","https://openalex.org/W775331923","https://openalex.org/W1484258769","https://openalex.org/W1501458753","https://openalex.org/W1506806321","https://openalex.org/W1662191912","https://openalex.org/W1916834241","https://openalex.org/W1932968309","https://openalex.org/W1968709559","https://openalex.org/W1970872899","https://openalex.org/W1994244061","https://openalex.org/W2009086942","https://openalex.org/W2023831651","https://openalex.org/W2039057510","https://openalex.org/W2046056978","https://openalex.org/W2050693797","https://openalex.org/W2057888214","https://openalex.org/W2090716422","https://openalex.org/W2112856142","https://openalex.org/W2121812409","https://openalex.org/W2129379984","https://openalex.org/W2138857742","https://openalex.org/W2143054781","https://openalex.org/W2144760012","https://openalex.org/W2145846419","https://openalex.org/W2153635508","https://openalex.org/W2159736522","https://openalex.org/W2167136086","https://openalex.org/W2180339972","https://openalex.org/W2288252882","https://openalex.org/W2395750323","https://openalex.org/W2395792107","https://openalex.org/W2397346386","https://openalex.org/W2397474108","https://openalex.org/W2397634864","https://openalex.org/W2400341349","https://openalex.org/W2402919203","https://openalex.org/W2405354182","https://openalex.org/W2405476549","https://openalex.org/W2405950182","https://openalex.org/W2407231000","https://openalex.org/W2407342067","https://openalex.org/W2483380302","https://openalex.org/W2485395001","https://openalex.org/W2488005896","https://openalex.org/W2493334087","https://openalex.org/W2587151953","https://openalex.org/W2606321545","https://openalex.org/W2614002621","https://openalex.org/W3145164839","https://openalex.org/W4246070010","https://openalex.org/W6604441197","https://openalex.org/W6605273041","https://openalex.org/W6622345507","https://openalex.org/W6637034065","https://openalex.org/W6640010188","https://openalex.org/W6680300913","https://openalex.org/W6712282327","https://openalex.org/W6712325649","https://openalex.org/W6712381122","https://openalex.org/W6712467859","https://openalex.org/W6713521420","https://openalex.org/W6713590052","https://openalex.org/W6714201320","https://openalex.org/W6714435555"],"related_works":["https://openalex.org/W1992796048","https://openalex.org/W2544498551","https://openalex.org/W2357561349","https://openalex.org/W2102592064","https://openalex.org/W4313224873","https://openalex.org/W2084443277","https://openalex.org/W2336335760","https://openalex.org/W2080861011","https://openalex.org/W2051257108","https://openalex.org/W2096727529"],"abstract_inverted_index":{"The":[0,97],"mismatch":[1],"between":[2],"enrollment":[3],"and":[4,128,155,183,192,215],"test":[5,126,184],"utterances":[6,185],"due":[7],"to":[8,40,44,66,104,116,173,219],"different":[9,72,193,221],"types":[10,77,222],"of":[11,50,71,89,95,110,120,190,201,223],"variabilities":[12],"is":[13,64,139,212,216],"a":[14,59,125,129,187],"great":[15],"challenge":[16],"in":[17,34,92,225],"speaker":[18],"verification.":[19],"Based":[20],"on":[21,163,206],"the":[22,25,48,68,86,93,101,111,117,132,136,143,148,153,158,169,197,209],"observation":[23],"that":[24,168],"SNR-level":[26],"variability":[27,30,224],"or":[28,46,75],"channel-type":[29],"causes":[31,100],"heterogeneous":[32],"clusters":[33],"i-vector":[35,112,127],"space,":[36],"this":[37],"paper":[38],"proposes":[39],"apply":[41],"supervised":[42],"learning":[43,49],"drive":[45],"guide":[47],"probabilistic":[51],"linear":[52],"discriminant":[53],"analysis":[54],"(PLDA)":[55],"mixture":[56,94,102,119,200],"models.":[57],"Specifically,":[58],"deep":[60],"neural":[61],"network":[62],"(DNN)":[63],"trained":[65],"produce":[67],"posterior":[69,87],"probabilities":[70,88],"SNR":[73,207],"levels":[74],"channel":[76,194],"given":[78,124],"i-vectors":[79],"as":[80,114],"input.":[81],"These":[82],"posteriors":[83,150],"then":[84],"replace":[85],"indicator":[90],"variables":[91],"PLDA.":[96,121],"discriminative":[98],"training":[99,182],"model":[103,211],"perform":[105],"more":[106,177,213],"reasonable":[107],"soft":[108],"divisions":[109],"space":[113],"compared":[115],"conventional":[118],"During":[122],"verification,":[123],"target-speaker's":[130],"i-vector,":[131],"marginal":[133],"likelihood":[134],"for":[135,157],"same-speaker":[137],"hypothesis":[138],"obtained":[140],"by":[141,147,152],"summing":[142],"component":[144,149],"likelihoods":[145],"weighted":[146],"produced":[151],"DNN,":[154],"likewise":[156],"different-speaker":[159],"hypothesis.":[160],"Results":[161],"based":[162],"NIST":[164],"2012":[165],"SRE":[166],"demonstrate":[167],"proposed":[170,210],"scheme":[171],"leads":[172],"better":[174],"performance":[175],"under":[176],"realistic":[178],"situations":[179],"where":[180],"both":[181],"cover":[186],"wide":[188],"range":[189],"SNRs":[191],"types.":[195],"Unlike":[196],"previous":[198],"SNR-dependent":[199],"PLDA":[202],"which":[203],"only":[204],"focuses":[205],"mismatch,":[208],"general":[214],"potentially":[217],"applicable":[218],"addressing":[220],"speech.":[226]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}