{"id":"https://openalex.org/W2043273367","doi":"https://doi.org/10.1109/slt.2014.7078603","title":"Spoken language mismatch in speaker verification: An investigation with NIST-SRE and CRSS Bi-Ling corpora","display_name":"Spoken language mismatch in speaker verification: An investigation with NIST-SRE and CRSS Bi-Ling corpora","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2043273367","doi":"https://doi.org/10.1109/slt.2014.7078603","mag":"2043273367"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2014.7078603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","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/A5103589192","display_name":"Abhinav Misra","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Abhinav Misra","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), The University of Texas at Dallas (UTD),, Richardson, TX, USA","Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering & Computer Science, The University of Texas at Dallas (UTD), Richardson, 75080-3021, USA"],"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), The University of Texas at Dallas (UTD),, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering & Computer Science, The University of Texas at Dallas (UTD), Richardson, 75080-3021, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H. L. Hansen","raw_affiliation_strings":["University of Texas at Dallas, Richardson, TX, US","Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering & Computer Science, The University of Texas at Dallas (UTD), Richardson, 75080-3021, USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas, Richardson, TX, US","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering & Computer Science, The University of Texas at Dallas (UTD), Richardson, 75080-3021, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103589192"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":3.2721,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.92850334,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"372","last_page":"377"},"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":0.9991000294685364,"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":0.9966999888420105,"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":0.8299234509468079},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.748099148273468},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7123953104019165},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6230612993240356},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5784921050071716},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5384665727615356},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5002138614654541},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.43702369928359985},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.43478843569755554}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8299234509468079},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.748099148273468},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7123953104019165},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6230612993240356},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5784921050071716},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5384665727615356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5002138614654541},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.43702369928359985},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.43478843569755554},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2014.7078603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W97107628","https://openalex.org/W1752971345","https://openalex.org/W1916834241","https://openalex.org/W2107638917","https://openalex.org/W2115638247","https://openalex.org/W2117486215","https://openalex.org/W2128653836","https://openalex.org/W2129120544","https://openalex.org/W2130375591","https://openalex.org/W2136879537","https://openalex.org/W2148488622","https://openalex.org/W2150659647","https://openalex.org/W2150769028","https://openalex.org/W2159736522","https://openalex.org/W2168561756","https://openalex.org/W2395750323","https://openalex.org/W2400341349","https://openalex.org/W2401594978","https://openalex.org/W2406312423","https://openalex.org/W6604007911","https://openalex.org/W6679364759","https://openalex.org/W6679444976","https://openalex.org/W6682365201","https://openalex.org/W6682600690","https://openalex.org/W6713727690"],"related_works":["https://openalex.org/W1968216131","https://openalex.org/W2355011896","https://openalex.org/W3089964815","https://openalex.org/W2206035908","https://openalex.org/W1581134722","https://openalex.org/W66821593","https://openalex.org/W2051274299","https://openalex.org/W2149220986","https://openalex.org/W2144470400","https://openalex.org/W2911612049"],"abstract_inverted_index":{"Compensation":[0],"for":[1,37,54],"mismatch":[2,23,36],"between":[3],"acoustic":[4],"conditions":[5],"in":[6,14,134,155,171,201,205],"automatic":[7],"speaker":[8,38,43,68,135,153,202],"recognition":[9,69],"has":[10,24,130],"been":[11],"widely":[12],"addressed":[13],"recent":[15],"years.":[16],"However,":[17],"performance":[18,70,204],"degradation":[19],"due":[20],"to":[21,26,82,94,109,173,186],"language":[22,55,64,114,156,209],"yet":[25],"be":[27],"thoroughly":[28],"addressed.":[29],"In":[30],"this":[31,176],"study,":[32],"we":[33,78,86,146,178],"address":[34],"langauge":[35],"verification.":[39],"We":[40,60],"select":[41],"bilingual":[42,163],"data":[44,93,126,140],"from":[45,141],"the":[46,95,111,142,188,206],"NIST":[47],"SRE":[48],"04-08":[49],"corpora":[50],"and":[51,57,103,195],"develop":[52],"train/test-trials":[53],"matched":[56],"mismatched":[58],"conditions.":[59],"first":[61],"show":[62,147,196],"that":[63,119],"variability":[65],"significantly":[66],"degrades":[67],"even":[71],"with":[72],"a":[73,131,180,197],"state-of-the-art":[74],"i-vector":[75],"system.":[76],"Next,":[77],"consider":[79],"two":[80,192],"ideas":[81],"improve":[83],"performance:":[84],"i)":[85],"introduce":[87],"small":[88,121],"amounts":[89,122],"of":[90,113,123,162,191,208],"multi-lingual":[91,124],"speech":[92,159],"Probabilistic":[96],"Linear":[97],"Discriminant":[98],"Analysis":[99],"(PLDA)":[100],"development":[101],"set,":[102],"ii)":[104],"explore":[105],"phoneme":[106,150,182],"level":[107],"analysis":[108],"investigate":[110],"effect":[112],"mismatch.":[115,157,210],"It":[116],"is":[117],"shown":[118],"introducing":[120],"seed":[125],"within":[127],"PLDA":[128],"training":[129],"significant":[132],"improvement":[133,200],"verification":[136,154,203],"performance.":[137],"Also,":[138],"using":[139],"CRSS":[143],"Bi-Ling":[144],"corpus,":[145,177],"how":[148],"various":[149],"classes":[151],"affect":[152],"This":[158],"corpus":[160],"consists":[161],"speakers":[164],"who":[165],"speak":[166],"either":[167],"Hindi":[168],"or":[169],"Mandarin,":[170],"addition":[172],"English.":[174],"Using":[175],"propose":[179],"novel":[181],"histogram":[183],"normalization":[184],"technique":[185],"match":[187],"phonetic":[189],"spaces":[190],"different":[193],"languages":[194],"+16.6%":[198],"relative":[199],"presence":[207]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}