{"id":"https://openalex.org/W1910206629","doi":"https://doi.org/10.1109/icassp.2003.1198776","title":"Symbolic speaker adaptation with phone inventory expansion","display_name":"Symbolic speaker adaptation with phone inventory expansion","publication_year":2003,"publication_date":"2003-11-20","ids":{"openalex":"https://openalex.org/W1910206629","doi":"https://doi.org/10.1109/icassp.2003.1198776","mag":"1910206629"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1198776","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198776","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/A5030671398","display_name":"Kyung-Tak Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I1333370159","display_name":"Motorola (United States)","ror":"https://ror.org/01hafxd32","country_code":"US","type":"company","lineage":["https://openalex.org/I1333370159"]},{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Kyung-Tak Lee","raw_affiliation_strings":["Institut Eur\u00e9com, Sophia Antipolis, France","Motorola Labs, Austin, TX, USA","Schaumburg (IL), Motorola Research Laboratories, Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Eur\u00e9com, Sophia Antipolis, France","institution_ids":["https://openalex.org/I1902872"]},{"raw_affiliation_string":"Motorola Labs, Austin, TX, USA","institution_ids":["https://openalex.org/I1333370159"]},{"raw_affiliation_string":"Schaumburg (IL), Motorola Research Laboratories, Austin, TX, USA","institution_ids":["https://openalex.org/I1333370159"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037754631","display_name":"Lynette Melnar","orcid":null},"institutions":[{"id":"https://openalex.org/I1333370159","display_name":"Motorola (United States)","ror":"https://ror.org/01hafxd32","country_code":"US","type":"company","lineage":["https://openalex.org/I1333370159"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"L. Melnar","raw_affiliation_strings":["Motorola Labs, Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Motorola Labs, Austin, TX, USA","institution_ids":["https://openalex.org/I1333370159"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063465754","display_name":"Jim Talley","orcid":null},"institutions":[{"id":"https://openalex.org/I1333370159","display_name":"Motorola (United States)","ror":"https://ror.org/01hafxd32","country_code":"US","type":"company","lineage":["https://openalex.org/I1333370159"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Talley","raw_affiliation_strings":["Motorola Labs, Austin, TX, USA","Schaumburg (IL), Motorola Research Laboratories, Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Motorola Labs, Austin, TX, USA","institution_ids":["https://openalex.org/I1333370159"]},{"raw_affiliation_string":"Schaumburg (IL), Motorola Research Laboratories, Austin, TX, USA","institution_ids":["https://openalex.org/I1333370159"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108525230","display_name":"C. Wellekens","orcid":null},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"C.J. Wellekens","raw_affiliation_strings":["Institut Eur\u00e9com, Sophia Antipolis, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Eur\u00e9com, Sophia Antipolis, France","institution_ids":["https://openalex.org/I1902872"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8343,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72741273,"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":"296"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9955000281333923,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9930999875068665,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.8137928247451782},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.8134149312973022},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7915189266204834},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7791876792907715},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7526315450668335},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5184497237205505},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.48613759875297546},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.466859370470047},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4420072138309479},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.41268086433410645},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.41098666191101074},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3835862874984741},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.356431782245636},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18052938580513},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10732218623161316},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07024481892585754}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8137928247451782},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.8134149312973022},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7915189266204834},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7791876792907715},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7526315450668335},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5184497237205505},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.48613759875297546},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.466859370470047},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4420072138309479},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.41268086433410645},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.41098666191101074},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3835862874984741},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.356431782245636},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18052938580513},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10732218623161316},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07024481892585754},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2003.1198776","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198776","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":[{"display_name":"Quality Education","score":0.5199999809265137,"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/W153989523","https://openalex.org/W251439765","https://openalex.org/W1594031697","https://openalex.org/W1953949349","https://openalex.org/W2053967299","https://openalex.org/W2145442306","https://openalex.org/W2330820318","https://openalex.org/W6606199742","https://openalex.org/W6609541008","https://openalex.org/W6624852173","https://openalex.org/W6641010790","https://openalex.org/W6663848509","https://openalex.org/W6681691225","https://openalex.org/W6843735874"],"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/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1521049138"],"abstract_inverted_index":{"This":[0],"paper":[1],"further":[2],"develops":[3],"a":[4,25,29,64,79,87,140,157],"previously":[5],"proposed":[6],"adaptation":[7,15,55,109,145],"method":[8,97],"for":[9,42,69,74,161],"speech":[10,32,65,112],"recognition":[11,75],"called":[12],"symbolic":[13],"speaker":[14],"(SSA).":[16],"The":[17,50,120],"basic":[18],"idea":[19],"of":[20,31,60,89,108,144,163],"SSA":[21,96,132],"is":[22,98],"to":[23,92,136],"model":[24],"speaker's":[26,80],"pronunciation":[27,48],"as":[28],"blend":[30],"varieties":[33],"(SVs)":[34],"-":[35,41],"regional":[36],"dialects":[37],"and":[38,111],"foreign":[39],"accents":[40],"which":[43],"the":[44,57,95,118],"system":[45,51],"has":[46],"existing":[47],"models.":[49],"determines":[52],"during":[53],"an":[54],"process":[56],"relative":[58],"applicability":[59],"those":[61],"models,":[62],"yielding":[63],"variety":[66],"profile":[67],"(SVP)":[68],"each":[70],"speaker.":[71],"Speaker-dependent":[72],"lexica":[73],"are":[76],"determined":[77],"from":[78,113],"SVP.":[81],"In":[82],"this":[83],"paper,":[84],"we":[85],"discuss":[86],"series":[88],"experiments":[90],"designed":[91],"analyze":[93],"how":[94],"affected":[99],"by":[100,117,126],"SV-balanced":[101],"training,":[102],"expanded":[103,128],"phone":[104,130],"inventories,":[105],"reduced":[106],"amounts":[107],"data,":[110],"SVs":[114],"not":[115],"modeled":[116],"system.":[119],"most":[121],"dramatic":[122],"improvements":[123],"were":[124],"obtained":[125],"using":[127,156],"(\"SV-inclusive\")":[129],"inventories.":[131],"was":[133],"also":[134],"shown":[135],"be":[137],"effective":[138],"with":[139],"very":[141],"small":[142],"number":[143],"sentences.":[146],"And,":[147],"SSA's":[148],"SV":[149,158],"blending":[150],"scheme":[151,160],"yields":[152],"higher":[153],"accuracy":[154],"than":[155],"classification":[159],"speakers":[162],"novel":[164],"(unseen)":[165],"SVs.":[166]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}