{"id":"https://openalex.org/W2077548500","doi":"https://doi.org/10.1109/apsipa.2014.7041619","title":"Discriminative scoring for speaker recognition based on I-vectors","display_name":"Discriminative scoring for speaker recognition based on I-vectors","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2077548500","doi":"https://doi.org/10.1109/apsipa.2014.7041619","mag":"2077548500"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2014.7041619","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2014.7041619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific","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/A5110195480","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0001-8932-6661"},"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":"Jun Wang","raw_affiliation_strings":["Center for Speaker and Language Technologies (CSLT) Tsinghua University, Beijing, P. R. China","Center for Speaker and Language Technologies (CSLT) Tsinghua University, Beijing 100084, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speaker and Language Technologies (CSLT) Tsinghua University, Beijing, P. R. China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Center for Speaker and Language Technologies (CSLT) Tsinghua University, Beijing 100084, P.R. 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 Speaker and Language Technologies (CSLT) Tsinghua University, Beijing, P. R. China","Center for Speaker and Language Technologies (CSLT) Tsinghua University, Beijing 100084, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speaker and Language Technologies (CSLT) Tsinghua University, Beijing, P. R. China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Center for Speaker and Language Technologies (CSLT) Tsinghua University, Beijing 100084, P.R. China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102831262","display_name":"Ziwei Zhu","orcid":"https://orcid.org/0000-0001-5653-8094"},"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":"Ziwei Zhu","raw_affiliation_strings":["Center for Speaker and Language Technologies (CSLT) Tsinghua University, Beijing, P. R. China","Center for Speaker and Language Technologies (CSLT) Tsinghua University, Beijing 100084, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speaker and Language Technologies (CSLT) Tsinghua University, Beijing, P. R. China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Center for Speaker and Language Technologies (CSLT) Tsinghua University, Beijing 100084, P.R. 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 Speaker and Language Technologies (CSLT) Tsinghua University, Beijing, P. R. China","Center for Speaker and Language Technologies (CSLT) Tsinghua University, Beijing 100084, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speaker and Language Technologies (CSLT) Tsinghua University, Beijing, P. R. China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Center for Speaker and Language Technologies (CSLT) Tsinghua University, Beijing 100084, P.R. China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Frank Soong","raw_affiliation_strings":["Microsoft Research Asia, Beijing, P. R. China","Microsoft Research Asia, Beijing 100084, RR. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, P. R. China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing 100084, RR. China","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9976999759674072,"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":0.9934999942779541,"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/discriminative-model","display_name":"Discriminative model","score":0.8663074970245361},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7605783939361572},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6907599568367004},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6735224723815918},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.633417546749115},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5813720226287842},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5548511147499084},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.5212231874465942},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4291583299636841},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.3387984037399292}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8663074970245361},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7605783939361572},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6907599568367004},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6735224723815918},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.633417546749115},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5813720226287842},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5548511147499084},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.5212231874465942},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4291583299636841},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3387984037399292}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2014.7041619","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2014.7041619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W17749540","https://openalex.org/W111477576","https://openalex.org/W1589137271","https://openalex.org/W1916834241","https://openalex.org/W2107638917","https://openalex.org/W2121415728","https://openalex.org/W2121812409","https://openalex.org/W2131734706","https://openalex.org/W2150769028","https://openalex.org/W2917756095","https://openalex.org/W6600721324","https://openalex.org/W6604441197","https://openalex.org/W6640010188"],"related_works":["https://openalex.org/W2146591867","https://openalex.org/W3148366653","https://openalex.org/W1197719229","https://openalex.org/W2381158726","https://openalex.org/W1992796048","https://openalex.org/W2129090883","https://openalex.org/W1516392727","https://openalex.org/W2379906719","https://openalex.org/W2412815366","https://openalex.org/W2181956362"],"abstract_inverted_index":{"The":[0],"popular":[1],"i-vector":[2,13,110,124],"approach":[3,107,141,186],"to":[4,37,60,127,202],"speaker":[5,26,39,66,90],"recognition":[6],"represents":[7,65],"a":[8,15,71,104,113],"speech":[9,180],"segment":[10],"as":[11],"an":[12,123],"in":[14,70,80,99,189],"low-dimensional":[16],"space.":[17,45],"It":[18],"is":[19,95,131,164],"well":[20],"known":[21],"that":[22,64,118,122,161,183],"i-vectors":[23],"involve":[24],"both":[25],"and":[27,30,67,91,152,167,194,198],"session":[28,68,92],"variances,":[29],"therefore":[31],"additional":[32],"discriminative":[33,105,140],"approaches":[34],"are":[35,171],"required":[36],"extract":[38],"information":[40,156],"from":[41,134],"the":[42,49,85,89,119,128,135,162,168,176,184,190,196],"`total":[43],"variance'":[44],"Among":[46],"various":[47],"methods,":[48],"probabilistic":[50],"linear":[51],"discriminant":[52],"analysis":[53],"(PLDA)":[54],"achieves":[55],"state-of-the-art":[56],"performance,":[57],"partly":[58],"due":[59],"its":[61,81],"generative":[62],"framework":[63],"variances":[69],"hierarchical":[72],"way.":[73],"A":[74],"disadvantage":[75],"of":[76,84],"PLDA,":[77],"however,":[78],"lies":[79],"Gaussian":[82],"assumption":[83],"prior/conditional":[86],"distributions":[87,151],"on":[88,145,149,175],"variables,":[93],"which":[94,108],"not":[96,143],"necessarily":[97],"true":[98],"reality.":[100],"This":[101,139],"paper":[102],"presents":[103],"scoring":[106],"models":[109],"pairs":[111],"using":[112],"neural":[114],"network":[115,163],"(NN)":[116],"so":[117],"posterior":[120],"probability":[121],"pair":[125],"belongs":[126],"same":[129],"person":[130],"read":[132],"off":[133],"NN":[136,197],"output":[137],"directly.":[138],"does":[142],"rely":[144],"any":[146],"artificial":[147],"assumptions":[148],"data":[150,170,181],"can":[153],"learn":[154],"speaker-related":[155],"with":[157],"sufficient":[158],"accuracy":[159],"provided":[160],"large":[165],"enough":[166],"training":[169],"abundant.":[172],"Our":[173],"experiments":[174],"NIST":[177],"SRE08":[178],"interview":[179],"demonstrated":[182],"NN-based":[185],"outperforms":[187],"PLDA":[188,199],"core":[191],"test":[192],"condition,":[193],"combining":[195],"scores":[200],"leads":[201],"further":[203],"gains.":[204]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}