{"id":"https://openalex.org/W3197858274","doi":"https://doi.org/10.21437/interspeech.2021-2121","title":"VAENAR-TTS: Variational Auto-Encoder Based Non-AutoRegressive Text-to-Speech Synthesis","display_name":"VAENAR-TTS: Variational Auto-Encoder Based Non-AutoRegressive Text-to-Speech Synthesis","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197858274","doi":"https://doi.org/10.21437/interspeech.2021-2121","mag":"3197858274"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-2121","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-2121","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/A5101486499","display_name":"Hui Lu","orcid":"https://orcid.org/0000-0002-7698-6262"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Hui Lu","raw_affiliation_strings":["Centre for Perceptual and Interactive Intelligence, CUHK","Dept. of Systems Engineering & Engineering Management, Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"Centre for Perceptual and Interactive Intelligence, CUHK","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"Dept. of Systems Engineering & Engineering Management, Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100667025","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0002-6527-5502"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Dept. of Systems Engineering & Engineering Management, Chinese University of Hong Kong","Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems,","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Dept. of Systems Engineering & Engineering Management, Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems,","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025119324","display_name":"Xixin Wu","orcid":"https://orcid.org/0000-0001-9543-1572"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xixin Wu","raw_affiliation_strings":["Department of Engineering, University of Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046019793","display_name":"Xu Li","orcid":"https://orcid.org/0000-0002-0697-774X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xu Li","raw_affiliation_strings":["Dept. of Systems Engineering & Engineering Management, Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"Dept. of Systems Engineering & Engineering Management, Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083463839","display_name":"Shiyin Kang","orcid":"https://orcid.org/0000-0001-8304-5260"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiyin Kang","raw_affiliation_strings":["Huya Inc., Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Huya Inc., Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037109470","display_name":"Xunying Liu","orcid":"https://orcid.org/0000-0001-6725-1160"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xunying Liu","raw_affiliation_strings":["Dept. of Systems Engineering & Engineering Management, Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"Dept. of Systems Engineering & Engineering Management, Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["Centre for Perceptual and Interactive Intelligence, CUHK","Dept. of Systems Engineering & Engineering Management, Chinese University of Hong Kong","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems,"],"affiliations":[{"raw_affiliation_string":"Centre for Perceptual and Interactive Intelligence, CUHK","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"Dept. of Systems Engineering & Engineering Management, Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems,","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101486499"],"corresponding_institution_ids":["https://openalex.org/I177725633","https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":0.6999,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.76522578,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3775","last_page":"3779"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9970999956130981,"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":0.9970999956130981,"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":0.9715999960899353,"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/T12031","display_name":"Speech and dialogue systems","score":0.9125000238418579,"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/autoregressive-model","display_name":"Autoregressive model","score":0.7747989892959595},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7081891298294067},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6563135385513306},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6123110055923462},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5926718711853027},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5715972781181335},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41702547669410706},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3327595889568329},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19582030177116394},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1206308901309967},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09455564618110657}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7747989892959595},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7081891298294067},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6563135385513306},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6123110055923462},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5926718711853027},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5715972781181335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41702547669410706},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3327595889568329},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19582030177116394},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1206308901309967},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09455564618110657},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-2121","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-2121","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6200000047683716}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2603945996","display_name":null,"funder_award_id":"62076144","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3744313044","display_name":null,"funder_award_id":"Social","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8955107213","display_name":null,"funder_award_id":"Major","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322942","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48"},{"id":"https://openalex.org/F4320335869","display_name":"National Social Science Fund of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W1665214252","https://openalex.org/W1836465849","https://openalex.org/W2095705004","https://openalex.org/W2102003408","https://openalex.org/W2133564696","https://openalex.org/W2766812927","https://openalex.org/W2903739847","https://openalex.org/W2946200149","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2970832665","https://openalex.org/W3015282541","https://openalex.org/W3026874504","https://openalex.org/W3033411150","https://openalex.org/W3038172701","https://openalex.org/W3092028330","https://openalex.org/W3125481789","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2937020545","https://openalex.org/W2795485067","https://openalex.org/W4286761151","https://openalex.org/W4375869018","https://openalex.org/W3151292345","https://openalex.org/W3207780827","https://openalex.org/W4226251144","https://openalex.org/W2973019895","https://openalex.org/W3021817009","https://openalex.org/W4304195479"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,57],"variational":[4],"auto-encoder":[5],"based":[6,15,79],"nonautoregressive":[7],"text-to-speech":[8],"(VAENAR-TTS)":[9],"model.The":[10],"autoregressive":[11],"TTS":[12,33],"(AR-TTS)":[13],"models":[14,35,50],"on":[16,52,80,125],"the":[17,44,61,64,85,88,92,120,126,129,135,143,146,152,156,166],"sequenceto-sequence":[18],"architecture":[19],"can":[20,29,83],"generate":[21,56],"high-quality":[22],"speech,":[23],"but":[24],"their":[25],"sequential":[26],"decoding":[27,46],"process":[28],"be":[30,40],"time-consuming.Recently,":[31],"non-autoregressive":[32,117],"(NAR-TTS)":[34],"have":[36],"been":[37],"shown":[38],"to":[39,55,154],"more":[41],"efficient":[42],"with":[43,171],"parallel":[45],"process.However,":[47],"these":[48],"NAR-TTS":[49,173],"rely":[51],"phoneme-level":[53,105],"durations":[54],"hard":[58,77],"alignment":[59,71,78,130,141],"between":[60,142],"text":[62,144],"and":[63,114,122,138,145],"spectrogram.Obtaining":[65],"duration":[66],"labels,":[67],"either":[68],"through":[69],"forced":[70],"or":[72],"knowledge":[73],"distillation,":[74],"is":[75,97,115,132,149,169],"cumbersome.Furthermore,":[76],"phoneme":[81],"expansion":[82],"degrade":[84],"naturalness":[86],"of":[87,95],"synthesized":[89],"speech.In":[90],"contrast,":[91],"proposed":[93],"model":[94,108],"VAENAR-TTS":[96,107,160],"an":[98],"end-to-end":[99],"approach":[100],"that":[101,159],"does":[102,109],"not":[103,110],"require":[104],"durations.The":[106],"contain":[111],"recurrent":[112],"structures":[113],"completely":[116],"in":[118,134,151],"both":[119],"training":[121],"inference":[123],"phases.Based":[124],"VAE":[127],"architecture,":[128],"information":[131],"encoded":[133],"latent":[136,147],"variable,":[137],"attention-based":[139],"soft":[140],"variable":[148],"used":[150],"decoder":[153],"reconstruct":[155],"spectrogram.Experiments":[157],"show":[158],"achieves":[161],"state-of-the-art":[162],"synthesis":[163,167],"quality,":[164],"while":[165],"speed":[168],"comparable":[170],"other":[172],"models.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}
