{"id":"https://openalex.org/W2102582131","doi":"https://doi.org/10.1109/icassp.2003.1198761","title":"Unsupervised class-based language model adaptation for spontaneous speech recognition","display_name":"Unsupervised class-based language model adaptation for spontaneous speech recognition","publication_year":2003,"publication_date":"2003-11-21","ids":{"openalex":"https://openalex.org/W2102582131","doi":"https://doi.org/10.1109/icassp.2003.1198761","mag":"2102582131"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1198761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198761","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":true,"oa_status":"green","oa_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100485169/ATD100000413/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089174135","display_name":"T. Yokoyama","orcid":"https://orcid.org/0000-0002-0766-4550"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"T. Yokoyama","raw_affiliation_strings":["Department of Computer Science, Tokyo Institute of Technology, Meguro, Japan","Department of Computer Science, Tokyo Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Meguro, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103015161","display_name":"Takahiro Shinozaki","orcid":"https://orcid.org/0000-0001-8114-8450"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"T. Shinozaki","raw_affiliation_strings":["Department of Computer Science, Tokyo Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084374665","display_name":"Koji Iwano","orcid":"https://orcid.org/0000-0002-7373-5353"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"K. Iwano","raw_affiliation_strings":["Department of Computer Science, Tokyo Institute of Technology, Meguro, Japan","Department of Computer Science, Tokyo Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Meguro, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009532108","display_name":"Sadaoki Furui","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"S. Furui","raw_affiliation_strings":["Department of Computer Science, Tokyo Institute of Technology, Meguro, Japan","Department of Computer Science, Tokyo Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Meguro, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":2.9165,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.9128652,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"236"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9786999821662903,"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/T12031","display_name":"Speech and dialogue systems","score":0.9623000025749207,"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/computer-science","display_name":"Computer science","score":0.8340506553649902},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7555460929870605},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6647135615348816},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.641091525554657},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6272673606872559},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6031484007835388},{"id":"https://openalex.org/keywords/cache-language-model","display_name":"Cache language model","score":0.5812415480613708},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.573294460773468},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5704612731933594},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5458829402923584},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.251933753490448},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1236814558506012},{"id":"https://openalex.org/keywords/universal-networking-language","display_name":"Universal Networking Language","score":0.12191572785377502}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8340506553649902},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7555460929870605},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6647135615348816},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.641091525554657},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6272673606872559},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6031484007835388},{"id":"https://openalex.org/C39608478","wikidata":"https://www.wikidata.org/wiki/Q5015979","display_name":"Cache language model","level":5,"score":0.5812415480613708},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.573294460773468},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5704612731933594},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5458829402923584},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.251933753490448},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1236814558506012},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.12191572785377502},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C129353971","wikidata":"https://www.wikidata.org/wiki/Q5156949","display_name":"Comprehension approach","level":3,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2003.1198761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198761","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:t2r2.star.titech.ac.jp:00090697","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100485169","pdf_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100485169/ATD100000413/","source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:00089562","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100484212","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:t2r2.star.titech.ac.jp:00090697","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100485169","pdf_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100485169/ATD100000413/","source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2102582131.pdf"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W37526647","https://openalex.org/W200479330","https://openalex.org/W1488377236","https://openalex.org/W1502984613","https://openalex.org/W1631260214","https://openalex.org/W2121227244","https://openalex.org/W2134237567","https://openalex.org/W2149992312","https://openalex.org/W2402326842","https://openalex.org/W6601563604","https://openalex.org/W6629199099","https://openalex.org/W6630257147","https://openalex.org/W6636811518","https://openalex.org/W6678277124","https://openalex.org/W6712914314"],"related_works":["https://openalex.org/W4255155614","https://openalex.org/W2394860946","https://openalex.org/W761725120","https://openalex.org/W2009170886","https://openalex.org/W2071315630","https://openalex.org/W2897427480","https://openalex.org/W2787311093","https://openalex.org/W1508853749","https://openalex.org/W1745277","https://openalex.org/W2944691285"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"an":[3],"unsupervised,":[4],"batch-type,":[5],"class-based":[6,35],"language":[7,36,49,57,68],"model":[8,37],"adaptation":[9],"method":[10,72],"for":[11,92],"spontaneous":[12,79],"speech":[13],"recognition.":[14],"The":[15,70,96],"word":[16,105,119],"classes":[17,29],"are":[18,63],"automatically":[19],"determined":[20],"by":[21],"maximizing":[22],"the":[23,28,55,60,66,76,89,94,113,118,124],"average":[24],"mutual":[25],"information":[26],"between":[27],"using":[30,45,65,103],"a":[31,46],"training":[32],"set.":[33],"A":[34],"is":[38],"built":[39],"based":[40],"on":[41],"recognition":[42,77,90],"hypotheses":[43],"obtained":[44],"general":[47,56],"word-based":[48],"model,":[50],"and":[51,81,107],"linearly":[52],"interpolated":[53],"with":[54],"model.":[58,69],"All":[59],"input":[61],"utterances":[62],"re-recognized":[64],"adapted":[67],"proposed":[71],"was":[73,82,99,126],"applied":[74],"to":[75,84,101],"of":[78,112],"presentations":[80],"found":[83,100],"be":[85,102],"effective":[86],"in":[87,108,117],"improving":[88],"accuracy":[91,120],"all":[93,123],"presentations.":[95],"best":[97],"condition":[98,110],"100":[104],"classes,":[106],"this":[109],"2.3%":[111],"absolute":[114],"value":[115],"improvement":[116],"averaged":[121],"over":[122],"speakers":[125],"achieved.":[127]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}