{"id":"https://openalex.org/W2015549073","doi":"https://doi.org/10.1109/icassp.2014.6854360","title":"Simplified VTS-based I-vector extraction in noise-robust speaker recognition","display_name":"Simplified VTS-based I-vector extraction in noise-robust speaker recognition","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2015549073","doi":"https://doi.org/10.1109/icassp.2014.6854360","mag":"2015549073"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101648572","display_name":"Yun Lei","orcid":"https://orcid.org/0000-0003-4572-6078"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun Lei","raw_affiliation_strings":["SRI International, Speech Technology and Research Laboratory, California, USA","Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Speech Technology and Research Laboratory, California, USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060382325","display_name":"Mitchell McLaren","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mitchell McLaren","raw_affiliation_strings":["SRI International, Speech Technology and Research Laboratory, California, USA","Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Speech Technology and Research Laboratory, California, USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056267912","display_name":"Luciana Ferrer","orcid":"https://orcid.org/0000-0002-0426-8683"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luciana Ferrer","raw_affiliation_strings":["SRI International, Speech Technology and Research Laboratory, California, USA","Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Speech Technology and Research Laboratory, California, USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103585404","display_name":"Nicolas Scheffer","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicolas Scheffer","raw_affiliation_strings":["SRI International, Speech Technology and Research Laboratory, California, USA","Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Speech Technology and Research Laboratory, California, USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":null,"first_page":"4037","last_page":"4041"},"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":0.9994000196456909,"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":0.9976000189781189,"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":0.7319808602333069},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6273472309112549},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5994837284088135},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5915066599845886},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4999663829803467},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.49620872735977173},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.49042341113090515},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47769883275032043},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.44466838240623474},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4304281175136566},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36342334747314453},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12050577998161316}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7319808602333069},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6273472309112549},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5994837284088135},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5915066599845886},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4999663829803467},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.49620872735977173},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.49042341113090515},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47769883275032043},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.44466838240623474},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4304281175136566},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36342334747314453},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12050577998161316},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6854360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W651157033","https://openalex.org/W1573570773","https://openalex.org/W2090716422","https://openalex.org/W2118497033","https://openalex.org/W2121812409","https://openalex.org/W2129066450","https://openalex.org/W2136879537","https://openalex.org/W2150769028","https://openalex.org/W2395750323","https://openalex.org/W2406312423","https://openalex.org/W6634340323","https://openalex.org/W6680375658","https://openalex.org/W6713727690"],"related_works":["https://openalex.org/W2118039276","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2029134149"],"abstract_inverted_index":{"A":[0],"vector":[1],"taylor":[2],"series":[3],"(VTS)":[4],"based":[5],"i-vector":[6,103,113],"extractor":[7],"was":[8,59],"recently":[9],"proposed":[10,144],"for":[11,35],"noise-robust":[12],"speaker":[13,114],"recognition":[14,115],"by":[15],"extracting":[16],"synthesized":[17],"clean":[18],"i-vectors":[19,133],"to":[20,74,87,92,108,154],"be":[21],"used":[22],"in":[23,33,72,82,137,147],"the":[24,50,77,101,111,121,124,138,155],"standard":[25,102],"system":[26],"back-end.":[27],"This":[28],"approach":[29,41,79],"brings":[30],"significant":[31,135],"improvements":[32,81,136],"accuracy":[34],"noisy":[36,139],"speech":[37],"conditions.":[38],"However,":[39],"this":[40,62],"incurred":[42],"such":[43],"a":[44,149],"large":[45,56,83,125],"computational":[46],"expense":[47],"that":[48,76,130,142],"using":[49,131],"state-of-the-art":[51,88,112],"model":[52],"size":[53],"or":[54],"evaluating":[55],"scale":[57,84],"evaluations":[58],"impractical.":[60],"In":[61,90],"work,":[63],"we":[64],"propose":[65],"an":[66],"efficient":[67],"simplification":[68,145],"scheme,":[69],"named":[70],"sVTS,":[71],"order":[73],"show":[75,129],"VTS":[78,157],"gives":[80],"applications":[85],"compared":[86],"systems.":[89],"contrast":[91],"VTS,":[93],"sVTS":[94,132],"generates":[95],"normalized":[96],"Baum-Welch":[97],"statistics":[98],"and":[99,123,141],"uses":[100],"model,":[104],"making":[105],"it":[106],"straightforward":[107],"employ":[109],"on":[110,119],"system.":[116],"Results":[117],"presented":[118],"both":[120],"PRISM":[122],"NIST":[126],"SRE'12":[127],"corpora":[128],"provides":[134],"conditions,":[140],"our":[143],"result":[146],"only":[148],"slight":[150],"degradation":[151],"with":[152],"respect":[153],"original":[156],"approach.":[158]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}