{"id":"https://openalex.org/W2963796886","doi":"https://doi.org/10.21437/interspeech.2018-1558","title":"Machine Speech Chain with One-shot Speaker Adaptation","display_name":"Machine Speech Chain with One-shot Speaker Adaptation","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2963796886","doi":"https://doi.org/10.21437/interspeech.2018-1558","mag":"2963796886"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1558","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","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/A5038296765","display_name":"Andros Tjandra","orcid":"https://orcid.org/0000-0003-1246-5908"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]},{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Andros Tjandra","raw_affiliation_strings":["RIKEN, Center for Advanced Intelligence Project AIP, Japan","Nara Institute of Science and Technology Graduate School of Information Science, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN, Center for Advanced Intelligence Project AIP, Japan","institution_ids":["https://openalex.org/I4210126580"]},{"raw_affiliation_string":"Nara Institute of Science and Technology Graduate School of Information Science, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]},{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Nara Institute of Science and Technology Graduate School of Information Science, Japan","RIKEN, Center for Advanced Intelligence Project AIP, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology Graduate School of Information Science, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"RIKEN, Center for Advanced Intelligence Project AIP, Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]},{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":["Nara Institute of Science and Technology Graduate School of Information Science, Japan","RIKEN, Center for Advanced Intelligence Project AIP, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology Graduate School of Information Science, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"RIKEN, Center for Advanced Intelligence Project AIP, Japan","institution_ids":["https://openalex.org/I4210126580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5038296765"],"corresponding_institution_ids":["https://openalex.org/I4210126580","https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":6.9861,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":{"value":0.97516465,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"887","last_page":"891"},"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/T10028","display_name":"Topic Modeling","score":0.9657999873161316,"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":0.9645000100135803,"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":0.8338375091552734},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7707983255386353},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7142406702041626},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6832132935523987},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43799135088920593},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.42904597520828247}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8338375091552734},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7707983255386353},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7142406702041626},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6832132935523987},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43799135088920593},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.42904597520828247},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2018-1558","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W950853366","https://openalex.org/W1524333225","https://openalex.org/W1630959083","https://openalex.org/W1921523184","https://openalex.org/W1924770834","https://openalex.org/W2024490156","https://openalex.org/W2094147890","https://openalex.org/W2120605154","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2150769028","https://openalex.org/W2327501763","https://openalex.org/W2331128040","https://openalex.org/W2519091744","https://openalex.org/W2526425061","https://openalex.org/W2604184139","https://openalex.org/W2612434969","https://openalex.org/W2899771611","https://openalex.org/W2962699523","https://openalex.org/W2962759037","https://openalex.org/W2964167449","https://openalex.org/W4235154690"],"related_works":["https://openalex.org/W1999004162","https://openalex.org/W2385242602","https://openalex.org/W2029134149","https://openalex.org/W1872566306","https://openalex.org/W2021573333","https://openalex.org/W2108439317","https://openalex.org/W1607020250","https://openalex.org/W2043069908","https://openalex.org/W1513862252","https://openalex.org/W2885553183"],"abstract_inverted_index":{"In":[0],"previous":[1],"work,":[2],"we":[3,82],"developed":[4],"a":[5,56,62,84,91,127,133,164],"closed-loop":[6],"speech":[7,21,58,86,140,160],"chain":[8,87,141],"model":[9,53,72,94],"based":[10],"on":[11],"deep":[12],"learning,":[13],"in":[14,68,163,167],"which":[15],"the":[16,19,37,71,96,101,139,148,158,168],"architecture":[17],"enabled":[18],"automatic":[20],"recognition":[22,93,169],"(ASR)":[23],"and":[24,46],"text-to-speech":[25],"synthesis":[26],"(TTS)":[27],"components":[28],"to":[29,76,105,116,123,150],"mutually":[30],"improve":[31,52],"their":[32],"performance.This":[33],"was":[34],"accomplished":[35],"by":[36,89,109],"two":[38],"parts":[39],"teaching":[40],"each":[41],"other":[42],"using":[43],"both":[44],"labeled":[45],"unlabeled":[47],"data.This":[48],"approach":[49],"could":[50,65],"significantly":[51],"performance":[54],"within":[55],"single-speaker":[57],"dataset,":[59],"but":[60],"only":[61,126],"slight":[63],"increase":[64],"be":[66],"gained":[67],"multi-speaker":[69],"tasks.Furthermore,":[70],"is":[73],"still":[74],"unable":[75],"handle":[77,106],"unseen":[78,107],"speakers.In":[79],"this":[80],"paper,":[81],"present":[83],"new":[85],"mechanism":[88],"integrating":[90],"speaker":[92,112,122,129,137],"inside":[95],"loop.We":[97],"also":[98,145],"propose":[99],"extending":[100],"capability":[102],"of":[103],"TTS":[104,115],"speakers":[108,155],"implementing":[110],"one-shot":[111,128],"adaptation.This":[113],"enables":[114],"mimic":[117],"voice":[118],"characteristics":[119,156],"from":[120,132,147,157],"one":[121],"another":[124],"with":[125],"sample,":[130],"even":[131],"text":[134],"without":[135],"any":[136],"information.In":[138],"loop":[142],"mechanism,":[143],"ASR":[144],"benefits":[146],"ability":[149],"further":[151],"learn":[152],"an":[153],"arbitrary":[154],"generated":[159],"waveform,":[161],"resulting":[162],"significant":[165],"improvement":[166],"rate.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":4}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}