{"id":"https://openalex.org/W2787133659","doi":"https://doi.org/10.1109/asru.2017.8268927","title":"Cross-domain speech recognition using nonparallel corpora with cycle-consistent adversarial networks","display_name":"Cross-domain speech recognition using nonparallel corpora with cycle-consistent adversarial networks","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2787133659","doi":"https://doi.org/10.1109/asru.2017.8268927","mag":"2787133659"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2017.8268927","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268927","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5102851028","display_name":"Masato Mimura","orcid":"https://orcid.org/0000-0002-2403-0680"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Mimura","raw_affiliation_strings":["Kyoto University, School of Informatics, Sakyo-ku, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University, School of Informatics, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110763152","display_name":"Shinsuke Sakai","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinsuke Sakai","raw_affiliation_strings":["Kyoto University, School of Informatics, Sakyo-ku, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University, School of Informatics, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Kyoto University, School of Informatics, Sakyo-ku, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University, School of Informatics, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"134","last_page":"140"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9987000226974487,"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":0.9912999868392944,"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/adversarial-system","display_name":"Adversarial system","score":0.7971686720848083},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7554733157157898},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.622764527797699},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5578189492225647},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4113302230834961},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4092203378677368},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08566582202911377}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7971686720848083},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7554733157157898},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.622764527797699},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5578189492225647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4113302230834961},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4092203378677368},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08566582202911377},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2017.8268927","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268927","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1522199561","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1665214252","https://openalex.org/W1973681148","https://openalex.org/W1989314204","https://openalex.org/W1995562189","https://openalex.org/W2099471712","https://openalex.org/W2160815625","https://openalex.org/W2168013545","https://openalex.org/W2184045248","https://openalex.org/W2194775991","https://openalex.org/W2289394825","https://openalex.org/W2296581541","https://openalex.org/W2331128040","https://openalex.org/W2405774341","https://openalex.org/W2408713104","https://openalex.org/W2502312327","https://openalex.org/W2533523411","https://openalex.org/W2548275288","https://openalex.org/W2950776302","https://openalex.org/W2962793481","https://openalex.org/W2962879692","https://openalex.org/W2963266252","https://openalex.org/W2964121744","https://openalex.org/W4295521014","https://openalex.org/W4320013936","https://openalex.org/W6631362777","https://openalex.org/W6637242042","https://openalex.org/W6702130928"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4310988119","https://openalex.org/W4285226279","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,42,60,82,186],"recognition":[2,43],"(ASR)":[3],"systems":[4],"often":[5],"does":[6],"not":[7],"perform":[8],"well":[9],"when":[10],"it":[11],"is":[12,56],"used":[13],"in":[14,27,31,197,199],"a":[15,37,51,73,91,138,143,176,218],"different":[16,32,64],"acoustic":[17,46,76],"domain":[18,75,88,185],"from":[19,62,84,103],"the":[20,85,104,108,149,154,159,200,203],"training":[21,72],"time,":[22],"such":[23,165],"as":[24,134,161,163],"utterances":[25],"spoken":[26],"noisy":[28],"environments":[29],"or":[30],"speaking":[33,219],"styles.":[34],"We":[35,94],"propose":[36],"novel":[38],"approach":[39],"to":[40,152,158,192,214],"cross-domain":[41],"based":[44],"on":[45],"feature":[47,156],"mappings":[48,124],"provided":[49],"by":[50],"deep":[52],"neural":[53],"network,":[54],"which":[55,115],"trained":[57,133],"using":[58,67,90,107,137,184,202],"nonparallel":[59],"corpora":[61],"two":[63],"domains":[65],"and":[66,127,142],"no":[68],"phone":[69],"labels.":[70],"For":[71],"target":[74,81,105],"model,":[77],"we":[78],"generate":[79,97],"\u201cfake\u201d":[80,98],"features":[83,89,100,106],"labeleld":[86],"source":[87,99],"mapping":[92,110,151,210],"Gf.":[93],"can":[95],"also":[96,212],"for":[101],"testing":[102],"backward":[109,150,209],"G":[111,121,125,128,167],"<sub":[112,129,168],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[113,130,169],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">b</sub>":[114,131,170],"has":[116],"been":[117],"learned":[118],"simultaneously":[119],"with":[120,217],"f.":[122],"The":[123,208],"f":[126],"are":[132],"adversarial":[135,140],"networks":[136],"conventional":[139],"loss":[141,145],"cycle-consistency":[144],"criterion":[146],"that":[147,166],"encourages":[148],"bring":[153],"translated":[155],"back":[157],"original":[160],"much":[162],"possible":[164],"(Gf":[171],"(x))":[172],"\u2248":[173],"x.":[174],"In":[175],"highly":[177],"challenging":[178],"task":[179],"of":[180],"model":[181],"adaptation":[182,221],"only":[183],"features,":[187],"our":[188],"method":[189],"achieved":[190],"up":[191],"16":[193],"%":[194],"relative":[195],"improvements":[196],"WER":[198],"evaluation":[201],"CHiME3":[204],"real":[205],"test":[206],"data.":[207],"was":[211],"confirmed":[213],"be":[215],"effective":[216],"style":[220],"task.":[222]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}