{"id":"https://openalex.org/W2040903810","doi":"https://doi.org/10.1109/slt.2014.7078544","title":"Efficient multi-lingual unsupervised acoustic model training under mismatch conditions","display_name":"Efficient multi-lingual unsupervised acoustic model training under mismatch conditions","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2040903810","doi":"https://doi.org/10.1109/slt.2014.7078544","mag":"2040903810"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2014.7078544","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078544","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","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/A5103871271","display_name":"Masahiro Saiko","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Masahiro Saiko","raw_affiliation_strings":["Spoken Language Communication Laboratory, National Institute of Information and Communication Technology, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Spoken Language Communication Laboratory, National Institute of Information and Communication Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059740393","display_name":"H. Yamamoto","orcid":"https://orcid.org/0000-0001-7966-2629"},"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":"Hitoshi Yamamoto","raw_affiliation_strings":["Information and Media Processing Laboratories, NEC Corporation, Kanagawa, Japan","Information and Media Processing, Laboratories, NEC Corporation, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"Information and Media Processing Laboratories, NEC Corporation, Kanagawa, Japan","institution_ids":["https://openalex.org/I118347220"]},{"raw_affiliation_string":"Information and Media Processing, Laboratories, NEC Corporation, Kanagawa, Japan","institution_ids":["https://openalex.org/I118347220"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084065446","display_name":"Ryosuke Isotani","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":"Ryosuke Isotani","raw_affiliation_strings":["Information and Media Processing Laboratories, NEC Corporation, Kanagawa, Japan","Information and Media Processing, Laboratories, NEC Corporation, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"Information and Media Processing Laboratories, NEC Corporation, Kanagawa, Japan","institution_ids":["https://openalex.org/I118347220"]},{"raw_affiliation_string":"Information and Media Processing, Laboratories, NEC Corporation, Kanagawa, Japan","institution_ids":["https://openalex.org/I118347220"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001601327","display_name":"Chiori Hori","orcid":"https://orcid.org/0000-0002-4201-7578"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chiori Hori","raw_affiliation_strings":["Spoken Language Communication Laboratory, National Institute of Information and Communication Technology, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Spoken Language Communication Laboratory, National Institute of Information and Communication Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103871271"],"corresponding_institution_ids":["https://openalex.org/I90023481"],"apc_list":null,"apc_paid":null,"fwci":0.818,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.80570307,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"24","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9973999857902527,"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/T10860","display_name":"Speech and Audio Processing","score":0.9959999918937683,"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":0.8198186755180359},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7175713181495667},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6001119017601013},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5765065550804138},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.565638542175293},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5385433435440063},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5297331213951111},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5171012878417969},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5017421245574951},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.48968103528022766},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4806736409664154},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43278783559799194},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4317716062068939},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.28554490208625793},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1008228063583374}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8198186755180359},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7175713181495667},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6001119017601013},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5765065550804138},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.565638542175293},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5385433435440063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5297331213951111},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5171012878417969},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5017421245574951},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.48968103528022766},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4806736409664154},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43278783559799194},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4317716062068939},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28554490208625793},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1008228063583374},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/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/slt.2014.7078544","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078544","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W22876683","https://openalex.org/W60702959","https://openalex.org/W66627554","https://openalex.org/W229329885","https://openalex.org/W1524333225","https://openalex.org/W1993882792","https://openalex.org/W1993952617","https://openalex.org/W1997309301","https://openalex.org/W2056786202","https://openalex.org/W2088275353","https://openalex.org/W2091746061","https://openalex.org/W2100969003","https://openalex.org/W2133267619","https://openalex.org/W2183077412","https://openalex.org/W2296029621","https://openalex.org/W2917668649","https://openalex.org/W6600969651","https://openalex.org/W6602397471","https://openalex.org/W6602682705","https://openalex.org/W6608974995","https://openalex.org/W6631362777","https://openalex.org/W6685898284","https://openalex.org/W6759815381"],"related_works":["https://openalex.org/W2150890698","https://openalex.org/W2401394187","https://openalex.org/W4245698648","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306","https://openalex.org/W1566315437","https://openalex.org/W4221142855","https://openalex.org/W2244609359"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,59,88,137,166],"new":[3],"multi-lingual":[4],"unsupervised":[5,29,92],"acoustic":[6,30,53,93],"model":[7],"(AM)":[8],"training":[9,150,190],"method":[10,45,161,186,191],"for":[11,51,91],"low-resourced":[12,38,60,89,138],"languages":[13,36,129],"under":[14,113],"mismatch":[15,79,105,114],"conditions.":[16],"In":[17,98],"those":[18],"languages,":[19,78],"there":[20],"is":[21,68,95],"very":[22],"limited":[23],"or":[24],"no":[25],"transcribed":[26],"speech.":[27],"Thus,":[28],"modeling":[31,94],"using":[32],"AMs":[33,75,122,152],"of":[34,76,87,127,136,151,155,170,176,183],"different":[35,63,77,128],"(not":[37],"languages)":[39],"has":[40,46],"been":[41],"proposed.":[42],"The":[43,159],"conventional":[44,185],"shown":[47],"to":[48,71,133,144],"be":[49],"effective":[50],"similar":[52],"conditions,":[54,115],"such":[55],"as":[56],"speaking-style,":[57],"between":[58,81,149],"language":[61,90,139],"and":[62,84,140,147,153,187,194],"languages.":[64],"However,":[65],"since":[66],"it":[67],"not":[69],"easy":[70],"prepare":[72],"the":[73,85,134,156,173,179,184,188],"matched":[74],"problem":[80],"each":[82],"AM":[83],"speech":[86,126],"practically":[96],"occurred.":[97],"this":[99,104],"paper,":[100],"we":[101,116],"deal":[102],"with":[103,125],"problem.":[106],"To":[107],"generate":[108],"more":[109],"accurate":[110],"automatic":[111],"transcriptions":[112,164],"introduce":[117],"two":[118],"things:":[119],"(1)":[120],"Initial":[121],"were":[123,192],"trained":[124],"that":[130],"was":[131],"mapped":[132],"phonemes":[135],"(2)":[141],"Iterative":[142],"process":[143],"switch":[145],"back":[146],"forth":[148],"adaptation":[154],"initial":[157],"AMs.":[158],"proposed":[160],"without":[162],"any":[163],"achieved":[165],"word":[167,180],"error":[168,181],"rate":[169],"32.1%":[171],"on":[172],"evaluation":[174],"set":[175],"IWSLT2011,":[177],"while":[178],"rates":[182],"supervised":[189],"39.3":[193],"22.7%,":[195],"respectively.":[196]},"counts_by_year":[{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}