{"id":"https://openalex.org/W2962944781","doi":"https://doi.org/10.21437/interspeech.2017-545","title":"Recursive Whitening Transformation for Speaker Recognition on Language Mismatched Condition","display_name":"Recursive Whitening Transformation for Speaker Recognition on Language Mismatched Condition","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2962944781","doi":"https://doi.org/10.21437/interspeech.2017-545","mag":"2962944781"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-545","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-545","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","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/A5020263683","display_name":"Suwon Shon","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Suwon Shon","raw_affiliation_strings":["Korea University"],"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021831317","display_name":"Seongkyu Mun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seongkyu Mun","raw_affiliation_strings":["Korea University"],"affiliations":[{"raw_affiliation_string":"Korea University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026204977","display_name":"Hanseok Ko","orcid":"https://orcid.org/0000-0002-8744-4514"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hanseok Ko","raw_affiliation_strings":["School of Electrical Engineering"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5020263683"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5851,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.77646486,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2869","last_page":"2873"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.998199999332428,"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":0.998199999332428,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9704999923706055,"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":0.9452000260353088,"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":0.8341546654701233},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.805418848991394},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6498590111732483},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6257266998291016},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.6156092882156372},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6039037704467773},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5578920841217041},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5302668809890747},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4964442849159241},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.47064322233200073},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4392387270927429},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4378890097141266},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43509477376937866},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.42678302526474},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42590227723121643},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4192996025085449},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15268293023109436},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07748246192932129},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06908532977104187}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8341546654701233},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.805418848991394},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6498590111732483},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6257266998291016},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.6156092882156372},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6039037704467773},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5578920841217041},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5302668809890747},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4964442849159241},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.47064322233200073},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4392387270927429},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4378890097141266},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43509477376937866},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.42678302526474},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42590227723121643},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4192996025085449},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15268293023109436},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07748246192932129},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06908532977104187},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2017-545","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-545","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W4287755480","https://openalex.org/W3113607506","https://openalex.org/W4297779039"],"abstract_inverted_index":{"Recently":[0],"in":[1,63],"speaker":[2,88],"recognition,":[3],"performance":[4,110],"degradation":[5],"due":[6],"to":[7,25,39,58],"the":[8,18,41,51,64,76,84,134,144],"channel":[9],"domain":[10],"mismatched":[11,43,149],"condition":[12,150],"has":[13],"been":[14],"actively":[15],"addressed.":[16,28],"However,":[17],"mismatches":[19],"arising":[20],"from":[21],"language":[22,42,148],"is":[23,48,56,86,126,151],"yet":[24],"be":[26],"sufficiently":[27],"This":[29],"paper":[30],"proposes":[31],"an":[32,103],"approach":[33],"which":[34,55,83,125],"employs":[35],"recursive":[36],"whitening":[37,53],"transformation":[38],"mitigate":[40],"condition.":[44],"The":[45,71],"proposed":[46,145],"method":[47,146],"based":[49,127],"on":[50,75,128,147],"multiple":[52],"transformation,":[54],"intended":[57],"remove":[59],"un-whitened":[60],"residual":[61],"components":[62],"dataset":[65,92,101],"associated":[66],"with":[67,138],"i-vector":[68],"length":[69],"normalization.":[70],"experiments":[72],"were":[73],"conducted":[74],"Speaker":[77],"Recognition":[78],"Evaluation":[79],"2016":[80],"trials":[81],"of":[82,94,143],"task":[85],"non-English":[87],"recognition":[89],"using":[90,118],"development":[91],"consist":[93],"both":[95],"a":[96,114,129],"large":[97],"scale":[98],"out-of-domain":[99],"(English)":[100],"and":[102,122],"extremely":[104],"low-quantity":[105],"in-domain":[106],"(non-English)":[107],"dataset.":[108],"For":[109],"comparison,":[111],"we":[112],"develop":[113],"state-of-":[115],"the-art":[116],"system":[117],"deep":[119],"neural":[120],"network":[121],"bottleneck":[123],"feature,":[124],"phonetically":[130],"aware":[131],"model.":[132],"From":[133],"experimental":[135],"results,":[136],"along":[137],"other":[139],"prior":[140],"studies,":[141],"effectiveness":[142],"validated.":[152]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}