{"id":"https://openalex.org/W2129429203","doi":"https://doi.org/10.1109/icassp.2006.1660201","title":"Unsupervised Adaptation of a Stochastic Language Model Using a Japanese Raw Corpus","display_name":"Unsupervised Adaptation of a Stochastic Language Model Using a Japanese Raw Corpus","publication_year":2006,"publication_date":"2006-08-03","ids":{"openalex":"https://openalex.org/W2129429203","doi":"https://doi.org/10.1109/icassp.2006.1660201","mag":"2129429203"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2006.1660201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660201","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","raw_type":"proceedings-article"},"type":"conference-paper","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/A5021294422","display_name":"Gakuto Kurata","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"G. Kurata","raw_affiliation_strings":["IBM Research, Tokyo Research Laboratory, IBM Japan Limited, Yamato, Kanagawa, Japan","IBM Res., IBM Japan Ltd., Kanagawa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Tokyo Research Laboratory, IBM Japan Limited, Yamato, Kanagawa, Japan","institution_ids":["https://openalex.org/I4210145865"]},{"raw_affiliation_string":"IBM Res., IBM Japan Ltd., Kanagawa","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001224773","display_name":"Shinsuke Mori","orcid":"https://orcid.org/0000-0001-8596-8667"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"S. Mori","raw_affiliation_strings":["IBM Research, Tokyo Research Laboratory, IBM Japan Limited, Yamato, Kanagawa, Japan","IBM Res., IBM Japan Ltd., Kanagawa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Tokyo Research Laboratory, IBM Japan Limited, Yamato, Kanagawa, Japan","institution_ids":["https://openalex.org/I4210145865"]},{"raw_affiliation_string":"IBM Res., IBM Japan Ltd., Kanagawa","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083574298","display_name":"Masafumi Nishimura","orcid":"https://orcid.org/0000-0001-7633-9340"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"M. Nishimura","raw_affiliation_strings":["IBM Research, Tokyo Research Laboratory, IBM Japan Limited, Yamato, Kanagawa, Japan","IBM Res., IBM Japan Ltd., Kanagawa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Tokyo Research Laboratory, IBM Japan Limited, Yamato, Kanagawa, Japan","institution_ids":["https://openalex.org/I4210145865"]},{"raw_affiliation_string":"IBM Res., IBM Japan Ltd., Kanagawa","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"1037"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9968000054359436,"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/T12031","display_name":"Speech and dialogue systems","score":0.9940000176429749,"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":0.9255787134170532},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.7006736397743225},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6748064160346985},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6471275091171265},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6351718306541443},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6270521879196167},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.6231788992881775},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5698491334915161},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5695496797561646},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5681572556495667},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5488609671592712},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5137971043586731},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.42623764276504517}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9255787134170532},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.7006736397743225},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6748064160346985},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6471275091171265},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6351718306541443},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6270521879196167},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.6231788992881775},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5698491334915161},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5695496797561646},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5681572556495667},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5488609671592712},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5137971043586731},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42623764276504517},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2006.1660201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660201","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W130046785","https://openalex.org/W1574901103","https://openalex.org/W1608515068","https://openalex.org/W1997644175","https://openalex.org/W2007619971","https://openalex.org/W2020073413","https://openalex.org/W2154756108","https://openalex.org/W6605292293","https://openalex.org/W7055655252"],"related_works":["https://openalex.org/W2140536630","https://openalex.org/W2391730868","https://openalex.org/W2759814045","https://openalex.org/W2736760277","https://openalex.org/W4386940087","https://openalex.org/W4386931226","https://openalex.org/W2118055728","https://openalex.org/W2184188632","https://openalex.org/W2364370872","https://openalex.org/W3159089150"],"abstract_inverted_index":{"The":[0],"target":[1,28,40,76],"uses":[2],"of":[3,17,38,74,91,137],"large":[4],"vocabulary":[5],"continuous":[6],"speech":[7],"recognition":[8],"(LVCSR)":[9],"systems":[10],"are":[11],"spreading.":[12],"It":[13],"takes":[14],"a":[15,21,44,52,61,70,79,129],"lot":[16],"time":[18,116],"to":[19,33,55,60,98,135],"build":[20],"good":[22],"LVCSR":[23,58,120],"system":[24,59,121],"specialized":[25],"for":[26,101,117],"the":[27,36,39,75,92,99,105,115,125],"domain":[29],"because":[30],"experts":[31],"need":[32],"manually":[34],"segment":[35,69],"corpus":[37,73],"domain,":[41],"which":[42],"is":[43,84,108],"labor-intensive":[45],"task.":[46],"In":[47,64,123],"this":[48,88],"paper,":[49],"we":[50,67,112],"propose":[51],"new":[53,62],"method":[54,107,127],"adapt":[56],"an":[57,119],"domain.":[63,77],"our":[65],"method,":[66],"stochastically":[68],"Japanese":[71],"raw":[72],"Then":[78],"domain-specific":[80,93],"language":[81],"model":[82],"(LM)":[83],"built":[85],"based":[86],"on":[87],"corpus.":[89],"All":[90],"words":[94],"can":[95,113],"be":[96],"added":[97],"lexicon":[100],"LVCSR.":[102],"Most":[103],"importantly,":[104],"proposed":[106,126],"fully":[109],"automatic.":[110],"Therefore,":[111],"reduce":[114],"introducing":[118],"drastically.":[122],"addition,":[124],"yielded":[128],"comparable":[130],"or":[131],"even":[132],"superior":[133],"performance":[134],"use":[136],"expensive":[138],"manual":[139],"segmentation":[140]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}