{"id":"https://openalex.org/W2167057710","doi":"https://doi.org/10.1109/icassp.2003.1198846","title":"Speaker adaptation by hierarchical EigenVoice","display_name":"Speaker adaptation by hierarchical EigenVoice","publication_year":2003,"publication_date":"2003-11-21","ids":{"openalex":"https://openalex.org/W2167057710","doi":"https://doi.org/10.1109/icassp.2003.1198846","mag":"2167057710"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1198846","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198846","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/A5084335268","display_name":"Yoshifumi Onishi","orcid":"https://orcid.org/0000-0001-6314-718X"},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Y. Onishi","raw_affiliation_strings":["Multimedia Research Laboratories, NEC Corporation Limited, Kawasaki, Japan","Multimedia Res. Labs, NEC Corp., Kawasaki, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Research Laboratories, NEC Corporation Limited, Kawasaki, Japan","institution_ids":["https://openalex.org/I118347220"]},{"raw_affiliation_string":"Multimedia Res. Labs, NEC Corp., Kawasaki, Japan","institution_ids":["https://openalex.org/I118347220"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109221979","display_name":"K.-I. Iso","orcid":null},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"K.-I. Iso","raw_affiliation_strings":["Multimedia Research Laboratories, NEC Corporation Limited, Kawasaki, Japan","Multimedia Res. Labs, NEC Corp., Kawasaki, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Research Laboratories, NEC Corporation Limited, Kawasaki, Japan","institution_ids":["https://openalex.org/I118347220"]},{"raw_affiliation_string":"Multimedia Res. Labs, NEC Corp., Kawasaki, Japan","institution_ids":["https://openalex.org/I118347220"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I118347220"],"apc_list":null,"apc_paid":null,"fwci":1.2499,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80779088,"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":"576"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9926000237464905,"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":0.9926000237464905,"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":0.7545491456985474},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7391332387924194},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7365690469741821},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.5474543571472168},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5181804299354553},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4842262268066406},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.45320677757263184},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43852829933166504},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4347938299179077},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4323571026325226},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4291844964027405},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.41743382811546326},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41065311431884766},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11699476838111877}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7545491456985474},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7391332387924194},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7365690469741821},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.5474543571472168},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5181804299354553},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4842262268066406},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.45320677757263184},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43852829933166504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4347938299179077},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4323571026325226},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4291844964027405},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.41743382811546326},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41065311431884766},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11699476838111877},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"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.2003.1198846","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198846","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W108537639","https://openalex.org/W1797032983","https://openalex.org/W2100969003","https://openalex.org/W2146871184","https://openalex.org/W2153190454","https://openalex.org/W2165108269"],"related_works":["https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2160650576","https://openalex.org/W1197719229","https://openalex.org/W2381158726","https://openalex.org/W1992796048","https://openalex.org/W2129090883","https://openalex.org/W1516392727","https://openalex.org/W2379906719","https://openalex.org/W2412815366"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,23,33,48],"novel":[3],"speaker":[4,78],"adaptation":[5,36,45,71,79],"method,":[6],"hierarchical":[7,24],"EigenVoice":[8],"(HEV).":[9],"This":[10],"method":[11],"extends":[12],"the":[13,17,42,62,70,76],"eigenvoice":[14],"through":[15],"clustering":[16],"Gaussian":[18],"components":[19],"of":[20,35,44,54,69],"HMMs":[21],"into":[22],"tree":[25],"structure.":[26],"It":[27],"enables":[28],"one":[29],"to":[30],"autonomously":[31],"control":[32],"number":[34],"parameters":[37],"(model":[38],"complexity)":[39],"depending":[40],"on":[41],"amount":[43],"utterances":[46],"from":[47],"new":[49],"speaker.":[50],"The":[51],"experimental":[52],"results":[53],"Japanese":[55],"large":[56],"vocabulary":[57],"continuous":[58],"speech":[59],"recognition":[60],"confirmed":[61],"significant":[63],"performance":[64],"increase":[65],"in":[66],"all":[67],"range":[68],"utterance":[72],"amounts":[73],"compared":[74],"with":[75],"conventional":[77],"methods.":[80]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}