{"id":"https://openalex.org/W3196308991","doi":"https://doi.org/10.21437/interspeech.2021-971","title":"GANSpeech: Adversarial Training for High-Fidelity Multi-Speaker Speech Synthesis","display_name":"GANSpeech: Adversarial Training for High-Fidelity Multi-Speaker Speech Synthesis","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3196308991","doi":"https://doi.org/10.21437/interspeech.2021-971","mag":"3196308991"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-971","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-971","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5073217180","display_name":"Jinhyeok Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135449","display_name":"NCSOFT (South Korea)","ror":"https://ror.org/03q4mza74","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210135449"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jinhyeok Yang","raw_affiliation_strings":["Speech AI Lab, NCSOFT, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Speech AI Lab, NCSOFT, Republic of Korea","institution_ids":["https://openalex.org/I4210135449"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060429696","display_name":"Jae\u2010sung Bae","orcid":"https://orcid.org/0000-0002-8270-0072"},"institutions":[{"id":"https://openalex.org/I4210135449","display_name":"NCSOFT (South Korea)","ror":"https://ror.org/03q4mza74","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210135449"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jae-Sung Bae","raw_affiliation_strings":["Speech AI Lab, NCSOFT, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Speech AI Lab, NCSOFT, Republic of Korea","institution_ids":["https://openalex.org/I4210135449"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073688244","display_name":"Taejun Bak","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135449","display_name":"NCSOFT (South Korea)","ror":"https://ror.org/03q4mza74","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210135449"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Taejun Bak","raw_affiliation_strings":["Speech AI Lab, NCSOFT, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Speech AI Lab, NCSOFT, Republic of Korea","institution_ids":["https://openalex.org/I4210135449"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010564936","display_name":"Young-Ik Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135449","display_name":"NCSOFT (South Korea)","ror":"https://ror.org/03q4mza74","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210135449"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Young-Ik Kim","raw_affiliation_strings":["Speech AI Lab, NCSOFT, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Speech AI Lab, NCSOFT, Republic of Korea","institution_ids":["https://openalex.org/I4210135449"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052468556","display_name":"Hoon Young Cho","orcid":"https://orcid.org/0000-0002-6850-6580"},"institutions":[{"id":"https://openalex.org/I4210135449","display_name":"NCSOFT (South Korea)","ror":"https://ror.org/03q4mza74","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210135449"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hoon-Young Cho","raw_affiliation_strings":["Speech AI Lab, NCSOFT, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Speech AI Lab, NCSOFT, Republic of Korea","institution_ids":["https://openalex.org/I4210135449"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5073217180"],"corresponding_institution_ids":["https://openalex.org/I4210135449"],"apc_list":null,"apc_paid":null,"fwci":1.9714,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.88740596,"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":"2202","last_page":"2206"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9966999888420105,"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":0.9945999979972839,"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":0.8161083459854126},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7401258945465088},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6192507147789001},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5521194934844971},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5443311929702759},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.47304004430770874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.457798033952713},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4430619478225708},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.42162972688674927},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.41071265935897827},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07552477717399597},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.060901373624801636}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8161083459854126},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7401258945465088},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6192507147789001},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5521194934844971},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5443311929702759},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.47304004430770874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.457798033952713},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4430619478225708},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.42162972688674927},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.41071265935897827},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07552477717399597},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.060901373624801636},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-971","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-971","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W2107831318","https://openalex.org/W2519091744","https://openalex.org/W2593414223","https://openalex.org/W2619368999","https://openalex.org/W2766812927","https://openalex.org/W2788357188","https://openalex.org/W2892620417","https://openalex.org/W2903739847","https://openalex.org/W2946200149","https://openalex.org/W2963373786","https://openalex.org/W2963609956","https://openalex.org/W2963800363","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W2972574864","https://openalex.org/W2973046048","https://openalex.org/W2994143516","https://openalex.org/W3015338123","https://openalex.org/W3016159759","https://openalex.org/W3024747869","https://openalex.org/W3033411150","https://openalex.org/W3092028330","https://openalex.org/W3094650042","https://openalex.org/W3095545636","https://openalex.org/W3097297926","https://openalex.org/W3097828251","https://openalex.org/W3114636111","https://openalex.org/W3128910262","https://openalex.org/W3150572638","https://openalex.org/W4294619240","https://openalex.org/W4297606427","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2696990509"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,106],"neural":[3],"multi-speaker":[4,43,77,89,118],"text-to-speech":[5],"(TTS)":[6],"models":[7],"have":[8],"enabled":[9],"the":[10,27,37,42,57,62,66,82,109,116,130],"generation":[11],"of":[12,29],"reasonably":[13],"good":[14],"speech":[15,28,59],"quality":[16],"with":[17,32,41],"a":[18,30,53,75,87,125],"single":[19],"model":[20,44,63,79],"and":[21,61,120,123],"made":[22],"it":[23],"possible":[24],"to":[25,36,56,86],"synthesize":[26],"speaker":[31,39],"limited":[33],"training":[34,84],"data.Finetuning":[35],"target":[38],"data":[40],"can":[45],"achieve":[46],"better":[47,126],"quality,":[48],"however,":[49],"there":[50],"still":[51],"exists":[52],"gap":[54],"compared":[55],"real":[58],"sample":[60],"depends":[64],"on":[65],"speaker.In":[67],"this":[68],"work,":[69],"we":[70,93],"propose":[71,94],"GANSpeech,":[72],"which":[73],"is":[74],"high-fidelity":[76],"TTS":[78,90],"that":[80],"adopts":[81],"adversarial":[83,107],"method":[85],"non-autoregressive":[88],"model.In":[91],"addition,":[92],"simple":[95],"but":[96],"efficient":[97],"automatic":[98],"scaling":[99],"methods":[100],"for":[101],"feature":[102],"matching":[103],"loss":[104],"used":[105],"training.In":[108],"subjective":[110],"listening":[111],"tests,":[112],"GANSpeech":[113],"significantly":[114],"outperformed":[115],"baseline":[117],"FastSpeech":[119],"FastSpeech2":[121],"models,":[122],"showed":[124],"MOS":[127],"score":[128],"than":[129],"speaker-specific":[131],"fine-tuned":[132],"FastSpeech2.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}