{"id":"https://openalex.org/W3097649098","doi":"https://doi.org/10.21437/interspeech.2020-1195","title":"Generative Adversarial Training Data Adaptation for Very Low-Resource Automatic Speech Recognition","display_name":"Generative Adversarial Training Data Adaptation for Very Low-Resource Automatic Speech Recognition","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3097649098","doi":"https://doi.org/10.21437/interspeech.2020-1195","mag":"3097649098"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1195","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5000803465","display_name":"Kohei Matsuura","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kohei Matsuura","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102851028","display_name":"Masato Mimura","orcid":"https://orcid.org/0000-0002-2403-0680"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masato Mimura","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110763152","display_name":"Shinsuke Sakai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shinsuke Sakai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2737","last_page":"2741"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.992900013923645,"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":0.9815000295639038,"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":0.8605977892875671},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7378991842269897},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6269012093544006},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5798779129981995},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5326753854751587},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5196691751480103},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49748852849006653},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4340880513191223},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42953240871429443},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4183262586593628},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4149106740951538},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4139522910118103},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.41101300716400146},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4109601080417633},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3332188129425049},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1668858528137207}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8605977892875671},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7378991842269897},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6269012093544006},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5798779129981995},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5326753854751587},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5196691751480103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49748852849006653},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4340880513191223},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42953240871429443},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4183262586593628},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4149106740951538},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4139522910118103},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.41101300716400146},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4109601080417633},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3332188129425049},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1668858528137207},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1195","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","display_name":"No poverty","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2146197305","https://openalex.org/W2134950286","https://openalex.org/W151018310","https://openalex.org/W3081187864","https://openalex.org/W2891480213","https://openalex.org/W4380605396","https://openalex.org/W3133352777","https://openalex.org/W209733029","https://openalex.org/W2008737763","https://openalex.org/W2584084702"],"abstract_inverted_index":{"It":[0],"is":[1,23,132],"important":[2],"to":[3,27,73,87,104,125,134],"transcribe":[4],"and":[5,18,94,151,166,185],"archive":[6],"speech":[7,20,69,92],"data":[8,70,93,130],"of":[9,15,46,65,67],"endangered":[10,33],"languages":[11,34],"for":[12,79,111],"preserving":[13],"heritages":[14],"verbal":[16],"culture":[17],"automatic":[19],"recognition":[21],"(ASR)":[22],"a":[24,63,106,119,127],"powerful":[25],"tool":[26],"facilitate":[28],"this":[29,77,81,112,115,141],"process.":[30],"However,":[31],"since":[32],"do":[35],"not":[36],"generally":[37],"have":[38,72],"large":[39],"corpora":[40],"with":[41,62,188],"many":[42],"speakers,":[43],"the":[44,89,99,135,163,173],"performance":[45],"ASR":[47,109],"models":[48],"trained":[49],"on":[50,145,162,172],"them":[51],"are":[52,59],"considerably":[53],"poor":[54],"in":[55,102,158],"general.":[56],"Nevertheless,":[57],"we":[58,85,117],"often":[60],"left":[61],"lot":[64],"recordings":[66],"spontaneous":[68],"that":[71,131],"be":[74],"transcribed.":[75],"In":[76],"work,":[78],"mitigating":[80],"speaker":[82,101,142],"sparsity":[83],"problem,":[84],"propose":[86],"convert":[88],"whole":[90],"training":[91,129,187],"make":[95],"it":[96],"sound":[97],"like":[98],"test":[100,136],"order":[103],"develop":[105],"highly":[107],"accurate":[108],"system":[110],"speaker.":[113],"For":[114],"purpose,":[116],"utilize":[118],"CycleGAN-based":[120],"non-parallel":[121],"voice":[122],"conversion":[123],"technology":[124],"forge":[126],"labeled":[128],"close":[133],"speaker's":[137],"speech.":[138],"We":[139,153],"evaluated":[140],"adaptation":[143,184],"approach":[144,177],"two":[146,179,190],"low-resource":[147],"corpora,":[148],"namely,":[149],"Ainu":[150,164],"Mboshi.":[152],"obtained":[154],"35-60%":[155],"relative":[156,168],"improvement":[157,169],"phone":[159],"error":[160],"rate":[161],"corpus,":[165],"40%":[167],"was":[170],"attained":[171],"Mboshi":[174],"corpus.":[175],"This":[176],"outperformed":[178],"conventional":[180],"methods":[181],"namely":[182],"unsupervised":[183],"multilingual":[186],"these":[189],"corpora.":[191]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}