{"id":"https://openalex.org/W4296069158","doi":"https://doi.org/10.21437/interspeech.2022-10115","title":"Training Text-To-Speech Systems From Synthetic Data: A Practical Approach For Accent Transfer Tasks","display_name":"Training Text-To-Speech Systems From Synthetic Data: A Practical Approach For Accent Transfer Tasks","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296069158","doi":"https://doi.org/10.21437/interspeech.2022-10115"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10115","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10115","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5028798274","display_name":"Lev Finkelstein","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lev Finkelstein","raw_affiliation_strings":["Google LLC,"],"affiliations":[{"raw_affiliation_string":"Google LLC,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003420204","display_name":"Heiga Zen","orcid":"https://orcid.org/0000-0002-8959-5471"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heiga Zen","raw_affiliation_strings":["Google LLC,"],"affiliations":[{"raw_affiliation_string":"Google LLC,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047134953","display_name":"Norman Casagrande","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Norman Casagrande","raw_affiliation_strings":["Google LLC,"],"affiliations":[{"raw_affiliation_string":"Google LLC,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105193799","display_name":"Chun-an Chan","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chun-an Chan","raw_affiliation_strings":["Google LLC,"],"affiliations":[{"raw_affiliation_string":"Google LLC,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101778490","display_name":"Jia Ye","orcid":"https://orcid.org/0000-0002-7242-6065"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ye Jia","raw_affiliation_strings":["Google LLC,"],"affiliations":[{"raw_affiliation_string":"Google LLC,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068330105","display_name":"Tom Kenter","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tom Kenter","raw_affiliation_strings":["Google LLC,"],"affiliations":[{"raw_affiliation_string":"Google LLC,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051113269","display_name":"Alex Petelin","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Petelin","raw_affiliation_strings":["Google LLC,"],"affiliations":[{"raw_affiliation_string":"Google LLC,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021278619","display_name":"Jonathan Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Shen","raw_affiliation_strings":["Google LLC,"],"affiliations":[{"raw_affiliation_string":"Google LLC,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031222393","display_name":"Vincent Wan","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vincent Wan","raw_affiliation_strings":["Google LLC,"],"affiliations":[{"raw_affiliation_string":"Google LLC,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433691","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0003-1100-4835"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Google LLC,"],"affiliations":[{"raw_affiliation_string":"Google LLC,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101011504","display_name":"Yonghui Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yonghui Wu","raw_affiliation_strings":["Google LLC,"],"affiliations":[{"raw_affiliation_string":"Google LLC,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031372035","display_name":"Robert G. Clark","orcid":"https://orcid.org/0000-0003-4368-5145"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert Clark","raw_affiliation_strings":["Google LLC,"],"affiliations":[{"raw_affiliation_string":"Google LLC,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5028798274"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.1446,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.80164844,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4571","last_page":"4575"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.951200008392334,"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":0.951200008392334,"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/T12031","display_name":"Speech and dialogue systems","score":0.9506999850273132,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8083613514900208},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.7515479326248169},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.63988196849823},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6045701503753662},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6018031239509583},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5691084265708923},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.47998782992362976},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4331498146057129}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8083613514900208},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.7515479326248169},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.63988196849823},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6045701503753662},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6018031239509583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5691084265708923},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.47998782992362976},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4331498146057129}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10115","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10115","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W2519091744","https://openalex.org/W2794490148","https://openalex.org/W2808706139","https://openalex.org/W2890402938","https://openalex.org/W2904459034","https://openalex.org/W2964138190","https://openalex.org/W2964199361","https://openalex.org/W2972473628","https://openalex.org/W3008480565","https://openalex.org/W3016151052","https://openalex.org/W3033411150","https://openalex.org/W3080626558","https://openalex.org/W3081488690","https://openalex.org/W3091928890","https://openalex.org/W3170366517","https://openalex.org/W4221144919","https://openalex.org/W4285881128","https://openalex.org/W4289383906","https://openalex.org/W4294619240","https://openalex.org/W4295731579","https://openalex.org/W4298580827"],"related_works":["https://openalex.org/W1980564716","https://openalex.org/W2739335048","https://openalex.org/W1506224037","https://openalex.org/W2151922127","https://openalex.org/W4237818736","https://openalex.org/W4367680763","https://openalex.org/W4252005663","https://openalex.org/W2365914832","https://openalex.org/W2011236994","https://openalex.org/W2352261042"],"abstract_inverted_index":{"Transfer":[0],"tasks":[1],"in":[2,51,88],"text-to-speech":[3],"(TTS)":[4],"synthesis":[5],"-where":[6],"one":[7,15],"or":[8],"more":[9],"aspects":[10,31],"of":[11,14,17,24,37,100],"the":[12,38,98,120],"speech":[13],"set":[16,23],"speakers":[18,25],"is":[19,40,95,111],"transferred":[20],"to":[21],"another":[22],"that":[26,41,43,62,119],"do":[27],"not":[28],"feature":[29],"these":[30],"originally":[32],"-remains":[33],"a":[34,69,77,84,90,101],"challenging":[35],"task.One":[36],"challenges":[39],"models":[42,121],"have":[44,49],"high-quality":[45,85],"transfer":[46,63,86],"capabilities":[47],"can":[48,64,128],"issues":[50],"stability,":[52],"making":[53],"them":[54],"impractical":[55],"for":[56,83,105],"user-facing":[57],"critical":[58],"tasks.This":[59],"paper":[60],"demonstrates":[61],"be":[65],"obtained":[66],"by":[67,76],"training":[68],"robust":[70,79],"TTS":[71,80,93],"system":[72,81,94],"on":[73,97,123],"data":[74,125],"generated":[75],"less":[78],"designed":[82,104],"task;":[87],"particular,":[89],"CHiVE-BERT":[91],"monolingual":[92],"trained":[96,122],"output":[99],"Tacotron":[102],"model":[103],"accent":[106,134],"transfer.While":[107],"some":[108],"quality":[109,131],"loss":[110],"inevitable":[112],"with":[113],"this":[114,126],"approach,":[115],"experimental":[116],"results":[117],"show":[118],"synthetic":[124],"way":[127],"produce":[129],"high":[130],"audio":[132],"displaying":[133],"transfer,":[135],"while":[136],"preserving":[137],"speaker":[138],"characteristics":[139],"such":[140],"as":[141],"speaking":[142],"style.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2023,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}