{"id":"https://openalex.org/W2398795550","doi":"https://doi.org/10.21437/interspeech.2015-284","title":"Full multicondition training for robust i-vector based speaker recognition","display_name":"Full multicondition training for robust i-vector based speaker recognition","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2398795550","doi":"https://doi.org/10.21437/interspeech.2015-284","mag":"2398795550"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-284","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","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/A5054254044","display_name":"Dayana Ribas","orcid":"https://orcid.org/0000-0003-3813-4998"},"institutions":[{"id":"https://openalex.org/I4210095957","display_name":"Advanced Technologies Application Center","ror":"https://ror.org/00pwma409","country_code":"CU","type":"nonprofit","lineage":["https://openalex.org/I4210095957"]}],"countries":["CU"],"is_corresponding":false,"raw_author_name":"Dayana Ribas","raw_affiliation_strings":["CENATAV (Cuba)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CENATAV (Cuba)","institution_ids":["https://openalex.org/I4210095957"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065635001","display_name":"Emmanuel Vincent","orcid":"https://orcid.org/0000-0002-0183-7289"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emmanuel Vincent","raw_affiliation_strings":["MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (France)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112869946","display_name":"Jos\u00e9 R. Calvo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095957","display_name":"Advanced Technologies Application Center","ror":"https://ror.org/00pwma409","country_code":"CU","type":"nonprofit","lineage":["https://openalex.org/I4210095957"]}],"countries":["CU"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Ram\u00f3n Calvo","raw_affiliation_strings":["CENATAV (Cuba)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CENATAV (Cuba)","institution_ids":["https://openalex.org/I4210095957"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7398,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.86094658,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1057","last_page":"1061"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/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/T11309","display_name":"Music and Audio Processing","score":0.9945999979972839,"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/speech-recognition","display_name":"Speech recognition","score":0.756608247756958},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6962635517120361},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.6520150899887085},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.640943169593811},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5920671820640564},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5405833125114441},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5123618841171265},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.5091883540153503},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5005950927734375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4609561264514923},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4549441337585449},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4219365119934082},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.41744959354400635},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4126480221748352},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.37740689516067505},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21589383482933044},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08423319458961487}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.756608247756958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6962635517120361},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.6520150899887085},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.640943169593811},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5920671820640564},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5405833125114441},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5123618841171265},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.5091883540153503},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5005950927734375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4609561264514923},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4549441337585449},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4219365119934082},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.41744959354400635},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4126480221748352},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.37740689516067505},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21589383482933044},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08423319458961487},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2015-284","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W102482883","https://openalex.org/W111477576","https://openalex.org/W120084310","https://openalex.org/W1981755271","https://openalex.org/W2100854157","https://openalex.org/W2101045344","https://openalex.org/W2112856142","https://openalex.org/W2121061347","https://openalex.org/W2121415728","https://openalex.org/W2129066450","https://openalex.org/W2148575186","https://openalex.org/W2334833135","https://openalex.org/W2395750323","https://openalex.org/W2413073931","https://openalex.org/W2568428461"],"related_works":["https://openalex.org/W2401089611","https://openalex.org/W4255044973","https://openalex.org/W2499802997","https://openalex.org/W2112059504","https://openalex.org/W2727729836","https://openalex.org/W1960256358","https://openalex.org/W2548037963","https://openalex.org/W2464377622","https://openalex.org/W2394963835","https://openalex.org/W2146197305"],"abstract_inverted_index":{"Multicondition":[0],"training":[1,67,109,134],"(MCT)":[2],"is":[3],"an":[4],"established":[5],"technique":[6],"to":[7,26,37,59,127,130,162],"handle":[8],"noisy":[9],"and":[10,31,43,74,99,135,141,154],"reverberant":[11],"conditions.":[12,76],"Previous":[13],"works":[14],"in":[15,91,113],"the":[16,38,44,60,63,66,70,97,100,105,108,122,147,159],"field":[17],"of":[18,62,65,72,88,94,107,121,139,149,158],"i-vector":[19],"based":[20],"speaker":[21],"recognition":[22],"have":[23],"applied":[24],"MCT":[25,84,90,138],"linear":[27],"discriminant":[28],"analysis":[29],"(LDA)":[30],"probabilistic":[32],"LDA":[33,140],"(PLDA),":[34],"but":[35],"not":[36],"universal":[39],"background":[40],"model":[41],"(UBM)":[42],"total":[45],"variability":[46],"(T)":[47],"matrix,":[48,102],"arguing":[49],"that":[50],"this":[51,78],"would":[52],"be":[53],"too":[54],"much":[55],"time":[56],"consuming":[57],"due":[58],"increase":[61],"size":[64,106],"set":[68,110],"by":[69],"number":[71],"noise":[73,116],"reverberation":[75],"In":[77],"paper,":[79],"we":[80],"propose":[81],"a":[82,119],"full":[83],"approach":[85],"which":[86],"consists":[87],"applying":[89],"all":[92],"stages":[93],"training,":[95],"including":[96],"UBM":[98],"T":[101],"while":[103],"keeping":[104],"fixed.":[111],"Experiments":[112],"highly":[114],"nonstationary":[115],"conditions":[117],"show":[118,155],"decrease":[120],"equal":[123],"error":[124],"rate":[125],"(EER)":[126],"14.16%":[128],"compared":[129],"17.90%":[131],"for":[132,137],"clean":[133],"18.08%":[136],"PLDA":[142],"only.":[143],"We":[144],"also":[145],"evaluate":[146],"impact":[148],"state-of-the-art":[150],"multichannel":[151],"speech":[152],"enhancement":[153],"further":[156],"reduction":[157],"EER":[160],"down":[161],"10.47%.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}