{"id":"https://openalex.org/W2128979084","doi":"https://doi.org/10.1109/icassp.2003.1198775","title":"Pervasive unsupervised adaptation for lecture speech transcription","display_name":"Pervasive unsupervised adaptation for lecture speech transcription","publication_year":2003,"publication_date":"2003-11-21","ids":{"openalex":"https://openalex.org/W2128979084","doi":"https://doi.org/10.1109/icassp.2003.1198775","mag":"2128979084"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1198775","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198775","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/A5044713040","display_name":"D. Willettt","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"D. Willettt","raw_affiliation_strings":["NTT Commun. Sci. Labs., NTT Corp., Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Commun. Sci. Labs., NTT Corp., Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050849172","display_name":"Thomas Niesler","orcid":"https://orcid.org/0000-0002-7341-1017"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]},{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP","ZA"],"is_corresponding":false,"raw_author_name":"T. Niesler","raw_affiliation_strings":["Electrical Engineering Department, University of Stellenbosch, South Africa","NTT Corporation, NTT Communication Science Laboratories, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering Department, University of Stellenbosch, South Africa","institution_ids":["https://openalex.org/I26092322"]},{"raw_affiliation_string":"NTT Corporation, NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030109648","display_name":"Erik McDermott","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"E. McDermott","raw_affiliation_strings":["NTT Corporation, NTT Communication Science Laboratories, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003119242","display_name":"Yoko MINAMI","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Y. Minami","raw_affiliation_strings":["NTT Corporation, NTT Communication Science Laboratories, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027443847","display_name":"Shigeru Katagiri","orcid":"https://orcid.org/0000-0003-4738-5385"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"S. Katagiri","raw_affiliation_strings":["NTT Corporation, NTT Communication Science Laboratories, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5044713040"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.25774226,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"292"},"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":0.9987999796867371,"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":0.998199999332428,"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/computer-science","display_name":"Computer science","score":0.8440538644790649},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.8387370705604553},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.716820478439331},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5888939499855042},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5552720427513123},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5366726517677307},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49106645584106445},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.46576881408691406},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.45994043350219727},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.4455377757549286},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4378885328769684},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42791375517845154},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.35050779581069946},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1103249192237854}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8440538644790649},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8387370705604553},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.716820478439331},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5888939499855042},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5552720427513123},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5366726517677307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49106645584106445},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.46576881408691406},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.45994043350219727},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.4455377757549286},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4378885328769684},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42791375517845154},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.35050779581069946},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1103249192237854},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2003.1198775","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198775","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":0.6600000262260437,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W182840523","https://openalex.org/W200479330","https://openalex.org/W1596940414","https://openalex.org/W1651108041","https://openalex.org/W1847142773","https://openalex.org/W1892722218","https://openalex.org/W2134773162","https://openalex.org/W2169518243","https://openalex.org/W2402326842","https://openalex.org/W6635521279","https://openalex.org/W6639688182","https://openalex.org/W6712914314"],"related_works":["https://openalex.org/W1566315437","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2594897229","https://openalex.org/W4290708361","https://openalex.org/W2050138804","https://openalex.org/W767271433","https://openalex.org/W2126322296","https://openalex.org/W2244609359","https://openalex.org/W2141404479"],"abstract_inverted_index":{"Unsupervised":[0],"adaptation":[1,40,56,114],"has":[2],"evolved":[3],"as":[4],"a":[5],"popular":[6],"approach":[7,98],"for":[8,38,68],"tuning":[9],"the":[10,54,71,75,105,117],"acoustic":[11],"models":[12,44],"of":[13,29,41,57,108],"speaker-independent":[14],"speech":[15,50,86],"recognition":[16],"systems":[17],"to":[18],"specific":[19],"speakers,":[20],"speaker":[21],"groups":[22],"or":[23],"channel":[24],"conditions":[25],"while":[26],"making":[27],"use":[28],"only":[30],"untranscribed":[31],"data.":[32],"This":[33],"study":[34],"focuses":[35],"on":[36,53,83,104],"procedures":[37],"unsupervised":[39],"other":[42],"probabilistic":[43],"that":[45,116],"are":[46,122],"involved":[47],"in":[48],"state-of-the-art":[49],"recognizers":[51],"and":[52,65,74,111],"joint":[55,106],"multiple":[58],"knowledge":[59],"sources.":[60],"In":[61],"particular,":[62],"we":[63],"outline":[64],"evaluate":[66],"approaches":[67],"adapting":[69],"both":[70],"language":[72,110],"model":[73,77,113],"pronunciation":[76,112],"(lexicon)":[78],"without":[79],"supervision.":[80],"Initial":[81],"experiments":[82],"off-line":[84],"lecture":[85],"transcription":[87],"achieved":[88],"small":[89],"but":[90],"promising":[91],"word":[92],"error":[93],"rate":[94],"improvements":[95,121],"with":[96],"each":[97],"applied":[99],"separately.":[100],"The":[101],"experimental":[102],"results":[103],"application":[107],"acoustic,":[109],"indicate":[115],"individually":[118],"achievable":[119],"performance":[120],"additive.":[123]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}