{"id":"https://openalex.org/W4225306880","doi":"https://doi.org/10.1109/icassp43922.2022.9746442","title":"Joint and Adversarial Training with ASR for Expressive Speech Synthesis","display_name":"Joint and Adversarial Training with ASR for Expressive Speech Synthesis","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225306880","doi":"https://doi.org/10.1109/icassp43922.2022.9746442"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746442","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100679701","display_name":"Kaili Zhang","orcid":"https://orcid.org/0000-0002-0761-1272"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kaili Zhang","raw_affiliation_strings":["Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China","Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107748760","display_name":"Gong Cheng","orcid":"https://orcid.org/0009-0004-0272-3541"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Gong","raw_affiliation_strings":["Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China","Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082286929","display_name":"Wenhuan Lu","orcid":"https://orcid.org/0000-0002-7951-8907"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhuan Lu","raw_affiliation_strings":["Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China","Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050763764","display_name":"Longbiao Wang","orcid":"https://orcid.org/0000-0002-4005-5036"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longbiao Wang","raw_affiliation_strings":["Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China","Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027428789","display_name":"Jianguo Wei","orcid":"https://orcid.org/0000-0002-8964-9759"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianguo Wei","raw_affiliation_strings":["Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China","Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100638487","display_name":"Dawei Liu","orcid":"https://orcid.org/0000-0002-2268-5632"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dawei Liu","raw_affiliation_strings":["Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China","Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100679701"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":0.1041,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.23713839,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"6322","last_page":"6326"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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":0.9983999729156494,"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":0.8247925043106079},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7764147520065308},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6617153882980347},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6573713421821594},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.6206813454627991},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.617923378944397},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5162723064422607},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.515684962272644},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4733462631702423},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4637383222579956},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46136847138404846},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4333184063434601}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8247925043106079},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7764147520065308},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6617153882980347},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6573713421821594},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6206813454627991},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.617923378944397},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5162723064422607},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.515684962272644},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4733462631702423},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4637383222579956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46136847138404846},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4333184063434601},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746442","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W38194800","https://openalex.org/W2327501763","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2885800352","https://openalex.org/W2904459034","https://openalex.org/W2906797124","https://openalex.org/W2914049472","https://openalex.org/W2963609956","https://openalex.org/W2963691546","https://openalex.org/W2964138190","https://openalex.org/W2964243274","https://openalex.org/W2998572311","https://openalex.org/W3015212100","https://openalex.org/W3015440759","https://openalex.org/W3016021263","https://openalex.org/W3033411150","https://openalex.org/W3160844600","https://openalex.org/W3196467321","https://openalex.org/W3196866316","https://openalex.org/W4295731579","https://openalex.org/W4298580827","https://openalex.org/W4395958073","https://openalex.org/W6748409065","https://openalex.org/W6749489859","https://openalex.org/W6750489868","https://openalex.org/W6757422803","https://openalex.org/W6772349387","https://openalex.org/W6778823374","https://openalex.org/W6865668308"],"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/W4288019534"],"abstract_inverted_index":{"Style":[0],"modeling":[1],"is":[2],"an":[3,111],"important":[4],"issue":[5],"and":[6,55,77,91,141,156],"has":[7],"been":[8],"proposed":[9],"in":[10,101],"expressive":[11],"speech":[12,58,155],"synthesis.":[13],"In":[14,62],"existing":[15],"unsupervised":[16],"methods,":[17],"the":[18,22,26,33,38,51,56,69,98,102,106,119,137,148,151,158,165],"style":[19,30,34,39,103,140,161],"encoder":[20,40],"extracts":[21],"latent":[23],"representation":[24],"from":[25,37,121],"reference":[27],"audio":[28],"as":[29],"information.":[31,104,143],"However,":[32],"information":[35,100],"extracted":[36],"will":[41,47,59],"entangle":[42],"some":[43],"content":[44,99,142],"information,":[45],"which":[46],"cause":[48],"conflicts":[49],"with":[50,83,164],"real":[52],"input":[53],"content,":[54],"synthesized":[57,154],"be":[60],"influenced.":[61],"this":[63],"study,":[64],"we":[65,109],"propose":[66,110],"to":[67,96,117],"alleviate":[68,136],"entanglement":[70,138],"problem":[71],"by":[72],"integrating":[73],"Text-To-Speech":[74],"(TTS)":[75],"model":[76,82,120],"Automatic":[78],"Speech":[79],"Recognition":[80],"(ASR)":[81],"a":[84],"share":[85],"layer":[86],"network":[87],"for":[88],"joint":[89],"training,":[90],"using":[92,126],"ASR":[93],"adversarial":[94,113],"training":[95],"eliminate":[97],"At":[105],"same":[107],"time,":[108],"adaptive":[112],"weight":[114],"learning":[115],"strategy":[116],"prevent":[118],"collapsing.":[122],"The":[123],"objective":[124],"evaluation":[125,145],"word":[127],"error":[128],"rate(WER)":[129],"demonstrates":[130],"that":[131,147],"our":[132],"method":[133,149],"can":[134],"effectively":[135],"between":[139],"Subjective":[144],"indicates":[146],"improves":[150],"quality":[152],"of":[153,160],"enhances":[157],"ability":[159],"transfer":[162],"compared":[163],"baseline":[166],"models.":[167]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
