{"id":"https://openalex.org/W2013891821","doi":"https://doi.org/10.1109/icassp.2002.5743791","title":"Speaker selection training for large vocabulary continuous speech recognition","display_name":"Speaker selection training for large vocabulary continuous speech recognition","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2013891821","doi":"https://doi.org/10.1109/icassp.2002.5743791","mag":"2013891821"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743791","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","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/A5009913582","display_name":"Chao Huang","orcid":"https://orcid.org/0000-0002-9300-1787"},"institutions":[{"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"],"is_corresponding":true,"raw_author_name":"Chao Huang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100708920","display_name":"Tao Chen","orcid":"https://orcid.org/0000-0002-5174-7687"},"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"]},{"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"],"is_corresponding":false,"raw_author_name":"Tao Chen","raw_affiliation_strings":["Department of Automation, Tsinghua University, China","Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087298985","display_name":"Eric Chang","orcid":"https://orcid.org/0000-0002-9678-5994"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Eric Chang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009913582"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":1.7754,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.85604113,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"2","issue":null,"first_page":"I","last_page":"609"},"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":0.9976999759674072,"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":0.9871000051498413,"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":0.801604151725769},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7985533475875854},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7093725800514221},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.7043490409851074},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.65940922498703},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6353185176849365},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6343572735786438},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6328179240226746},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6042931079864502},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6033114194869995},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42761147022247314},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06850707530975342}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.801604151725769},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7985533475875854},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7093725800514221},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7043490409851074},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.65940922498703},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6353185176849365},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6343572735786438},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6328179240226746},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6042931079864502},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6033114194869995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42761147022247314},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06850707530975342},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2002.5743791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743791","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.800000011920929,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W108550785","https://openalex.org/W121880762","https://openalex.org/W124356247","https://openalex.org/W164321059","https://openalex.org/W167743276","https://openalex.org/W1993259959","https://openalex.org/W2131118559","https://openalex.org/W2141132023","https://openalex.org/W2146871184","https://openalex.org/W6604322312","https://openalex.org/W6604897345","https://openalex.org/W6605133283","https://openalex.org/W6606631412","https://openalex.org/W6606746019"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W4247736853","https://openalex.org/W1992908141","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W4245698648","https://openalex.org/W2125642021","https://openalex.org/W1521049138"],"abstract_inverted_index":{"Acoustic":[0],"variability":[1],"across":[2],"speakers":[3,98,137],"is":[4,69,75],"one":[5,73],"of":[6,9,33,36,57,59,66,93,95,101,127,145],"the":[7,34,131,135,141],"challenges":[8],"speaker":[10,21,50,80,105],"independent":[11],"(SI)":[12],"speech":[13],"recognition":[14],"systems.":[15],"As":[16],"a":[17],"powerful":[18],"solution,":[19],"dominant":[20],"adaptation":[22,46,114],"technologies":[23],"such":[24,122],"as":[25,123],"MLLR":[26,113],"and":[27,86,99,110,138],"MAP":[28],"may":[29],"become":[30],"inefficient":[31],"because":[32],"lack":[35],"enough":[37],"enrollment":[38],"data.":[39],"In":[40,90],"this":[41],"paper,":[42],"we":[43],"propose":[44],"an":[45],"method":[47],"based":[48,88],"on":[49],"selection":[51,81],"training,":[52],"which":[53],"makes":[54],"full":[55],"use":[56],"statistics":[58],"training":[60],"corpus.":[61],"Relative":[62],"error":[63],"rate":[64],"reduction":[65],"5.31":[67],"%":[68],"achieved":[70],"when":[71],"only":[72],"utterance":[74],"available.":[76],"We":[77],"compare":[78],"different":[79],"strategies,":[82],"namely.":[83],"PCA,":[84],"HMM":[85],"GMM":[87],"methods.":[89],"addition,":[91],"impacts":[92],"number":[94,100,126],"selected":[96,128,136],"cohort":[97],"utterances":[102],"from":[103],"target":[104],"are":[106,115,150],"investigated.":[107],"Furthermore,":[108],"comparison":[109],"integration":[111],"with":[112,147],"also":[116,151],"shown.":[117],"Finally,":[118],"some":[119],"ongoing":[120],"work":[121],"dynamicalJy":[124],"varying":[125],"speakers,":[129],"measuring":[130],"relative":[132],"contribution":[133],"among":[134],"speeding":[139],"up":[140],"computationally":[142],"expensive":[143],"procedure":[144],"re-estimation":[146],"model":[148],"synthesis":[149],"discussed.":[152]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}