{"id":"https://openalex.org/W1921130144","doi":"https://doi.org/10.1109/icassp.2003.1198847","title":"Combining EigenVoices and structural MLLR for speaker adaptation","display_name":"Combining EigenVoices and structural MLLR for speaker adaptation","publication_year":2003,"publication_date":"2003-11-21","ids":{"openalex":"https://openalex.org/W1921130144","doi":"https://doi.org/10.1109/icassp.2003.1198847","mag":"1921130144"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1198847","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198847","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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/A5082374448","display_name":"Fabrice Lauri","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"F. Lauri","raw_affiliation_strings":["LORIA - INRIA, Speech Group, Vandoeuvre-l\u00e8s-Nancy, FRANCE","Speech Group, LORIA-INPL, Vandoeuvre-les-Nancy, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LORIA - INRIA, Speech Group, Vandoeuvre-l\u00e8s-Nancy, FRANCE","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210121838"]},{"raw_affiliation_string":"Speech Group, LORIA-INPL, Vandoeuvre-les-Nancy, France","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I4210121838"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072954623","display_name":"I. Mina","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"I. Mina","raw_affiliation_strings":["Speech Group, LORIA-INPL, Vandoeuvre-les-Nancy, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Group, LORIA-INPL, Vandoeuvre-les-Nancy, France","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I4210121838"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046546502","display_name":"Dominique Fohr","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"D. Fohr","raw_affiliation_strings":["LORIA - INRIA, Speech Group, Vandoeuvre-l\u00e8s-Nancy, FRANCE","Speech Group, LORIA-INPL, Vandoeuvre-les-Nancy, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LORIA - INRIA, Speech Group, Vandoeuvre-l\u00e8s-Nancy, FRANCE","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210121838"]},{"raw_affiliation_string":"Speech Group, LORIA-INPL, Vandoeuvre-les-Nancy, France","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I4210121838"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8343,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72946612,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"580"},"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":0.9965999722480774,"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":0.9934999942779541,"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/adaptation","display_name":"Adaptation (eye)","score":0.8075368404388428},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7997963428497314},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7495604753494263},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6817834377288818},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4986131191253662},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4742659330368042},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.43149811029434204},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4293532073497772},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.42505279183387756}],"concepts":[{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.8075368404388428},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7997963428497314},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7495604753494263},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6817834377288818},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4986131191253662},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4742659330368042},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.43149811029434204},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4293532073497772},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.42505279183387756},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2003.1198847","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198847","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.727.701","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.727.701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.multiagent.fr/extensions/ICAPManager/pdf/LauriIllinaFohr2003.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:inria-00099746v1","is_oa":false,"landing_page_url":"https://inria.hal.science/inria-00099746","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP'03, Apr 2003, Hong Kong, China, 4 p","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W137536304","https://openalex.org/W1485038873","https://openalex.org/W1544854900","https://openalex.org/W1953949349","https://openalex.org/W1958042395","https://openalex.org/W2100938666","https://openalex.org/W2122625394","https://openalex.org/W2146871184","https://openalex.org/W2149175990","https://openalex.org/W2165108269","https://openalex.org/W6605663675","https://openalex.org/W6629029613","https://openalex.org/W6632576651"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W1992908141","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509"],"abstract_inverted_index":{"This":[0],"paper":[1],"considers":[2],"the":[3,23,39,43,56,62,65,74,79,100,113,119],"problem":[4],"of":[5,8,25,42,64,73,81,102],"speaker":[6,44],"adaptation":[7,91,103],"acoustic":[9],"models":[10,46],"in":[11,88],"speech":[12,57,84],"recognition.":[13],"We":[14],"have":[15],"investigated":[16],"four":[17],"different":[18],"possible":[19],"methods":[20,76],"which":[21],"integrate":[22],"concepts":[24],"both":[26],"Structural":[27],"Maximum":[28],"Likelihood":[29],"Linear":[30],"Regression":[31],"(SMLLR)":[32],"and":[33,96],"EigenVoices-based":[34,97],"technique":[35],"(EV)":[36],"to":[37],"adapt":[38],"Gaussian":[40],"means":[41],"independent":[45],"for":[47],"a":[48],"new":[49],"speaker.":[50],"The":[51],"experiments":[52],"were":[53],"evaluated":[54],"using":[55],"recognition":[58,85],"engine":[59],"ESPERE":[60],"on":[61],"data":[63,104],"corpus":[66],"Resource":[67],"Management.":[68],"They":[69],"show":[70],"that":[71],"all":[72],"proposed":[75],"can":[77],"improve":[78],"performances":[80],"an":[82,108],"automatic":[83],"system":[86],"(ASRS)":[87],"supervised":[89],"batch":[90],"as":[92,94],"efficiently":[93],"SMLLR":[95,115],"techniques":[98],"whatever":[99],"amount":[101],"is":[105],"available.":[106],"For":[107],"unsupervised":[109],"incremental":[110],"adaptation,":[111],"only":[112],"approach":[114],"+":[116],"SEV":[117],"gives":[118],"best":[120],"results.":[121]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}