{"id":"https://openalex.org/W4382371192","doi":"https://doi.org/10.1109/taslp.2023.3290423","title":"Unsupervised TTS Acoustic Modeling for TTS With Conditional Disentangled Sequential VAE","display_name":"Unsupervised TTS Acoustic Modeling for TTS With Conditional Disentangled Sequential VAE","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4382371192","doi":"https://doi.org/10.1109/taslp.2023.3290423"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3290423","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3290423","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5108846913","display_name":"Jiachen Lian","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jiachen Lian","raw_affiliation_strings":["Tencent AI Lab Bellevue, Bellevue, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab Bellevue, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005304261","display_name":"Chunlei Zhang","orcid":"https://orcid.org/0000-0002-3851-2357"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chunlei Zhang","raw_affiliation_strings":["Tencent AI Lab Bellevue, Bellevue, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3851-2357","affiliations":[{"raw_affiliation_string":"Tencent AI Lab Bellevue, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068922218","display_name":"Gopala K. Anumanchipalli","orcid":"https://orcid.org/0000-0002-9714-7740"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gopala K. Anumanchipalli","raw_affiliation_strings":["EECS, UC Berkeley, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EECS, UC Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab Bellevue, Bellevue, WA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0520-6844","affiliations":[{"raw_affiliation_string":"Tencent AI Lab Bellevue, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5108846913"],"corresponding_institution_ids":["https://openalex.org/I4210108985"],"apc_list":null,"apc_paid":null,"fwci":1.3234,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84159982,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"31","issue":null,"first_page":"2548","last_page":"2557"},"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":0.9977999925613403,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9951000213623047,"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":0.7690857648849487},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6816406846046448},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.5649802088737488},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.47148820757865906},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.46729615330696106},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45974212884902954},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.45894020795822144},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.4276938736438751},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.41790586709976196}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7690857648849487},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6816406846046448},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.5649802088737488},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.47148820757865906},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.46729615330696106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45974212884902954},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.45894020795822144},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.4276938736438751},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.41790586709976196},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3290423","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3290423","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2073459066","https://openalex.org/W2104663520","https://openalex.org/W2187089797","https://openalex.org/W2747874407","https://openalex.org/W2758785877","https://openalex.org/W2802973008","https://openalex.org/W2808706139","https://openalex.org/W2945478979","https://openalex.org/W2946200149","https://openalex.org/W2952161038","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W2998572311","https://openalex.org/W3015734344","https://openalex.org/W3026874504","https://openalex.org/W3033411150","https://openalex.org/W3034603995","https://openalex.org/W3036167779","https://openalex.org/W3092028330","https://openalex.org/W3097538987","https://openalex.org/W3122011104","https://openalex.org/W3126283728","https://openalex.org/W3140429000","https://openalex.org/W3161704465","https://openalex.org/W3169905056","https://openalex.org/W3198869563","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3210384560","https://openalex.org/W4224612669","https://openalex.org/W4225329057","https://openalex.org/W4280552695","https://openalex.org/W4287173589","https://openalex.org/W4290995108","https://openalex.org/W4296070453","https://openalex.org/W4297841354","https://openalex.org/W4319862670","https://openalex.org/W6631190155","https://openalex.org/W6668990524","https://openalex.org/W6745117592","https://openalex.org/W6752753409","https://openalex.org/W6752888775","https://openalex.org/W6762533536","https://openalex.org/W6763832098","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6779823529","https://openalex.org/W6783867762","https://openalex.org/W6788996426","https://openalex.org/W6790622591","https://openalex.org/W6795952400","https://openalex.org/W6796464841","https://openalex.org/W6803240769","https://openalex.org/W6849880362"],"related_works":["https://openalex.org/W2500371832","https://openalex.org/W2079655441","https://openalex.org/W1524071955","https://openalex.org/W2912293245","https://openalex.org/W1604114751","https://openalex.org/W4252942110","https://openalex.org/W2032941915","https://openalex.org/W2075706796","https://openalex.org/W2549308614","https://openalex.org/W3018584924"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,82,114,141],"propose":[4],"a":[5,23,36,46,50,116,136,166,182,195],"novel":[6],"unsupervised":[7,104],"textto-speech":[8],"acoustic":[9],"model":[10],"training":[11],"scheme,":[12],"named":[13],"UTTS,":[14],"which":[15,98,126,175],"does":[16],"not":[17],"require":[18],"text-audio":[19],"pairs.":[20],"UTTS":[21,96,112,206],"is":[22,33,127,176],"multi-speaker":[24],"speech":[25,40,68,74,191,209],"synthesizer":[26],"that":[27,147,205],"supports":[28],"zero-shot":[29],"voice":[30],"cloning,":[31],"it":[32],"developed":[34],"from":[35],"perspective":[37],"of":[38,49,210],"disentangled":[39],"representation":[41,69],"learning.":[42],"The":[43],"framework":[44],"offers":[45,99],"flexible":[47],"choice":[48],"speaker's":[51],"duration":[52,138],"model,":[53],"timbre":[54],"feature":[55],"(identity)":[56],"and":[57,165,213,218],"content":[58,101],"for":[59,78],"TTS":[60,159,197],"inference.":[61],"We":[62,185],"leverage":[63],"recent":[64],"advancements":[65],"in":[66,199],"self-supervised":[67,158],"learning":[70],"as":[71,73,93,107,156],"well":[72],"synthesis":[75,192],"frontend":[76],"techniques":[77],"system":[79],"development.":[80],"Specifically,":[81],"employ":[83],"our":[84,188,226],"recently":[85],"formulated":[86],"Conditional":[87],"Disentangled":[88],"Sequential":[89],"Variational":[90],"Auto-encoder":[91],"(C-DSVAE)":[92],"the":[94,123,130,153,157,162,172],"backbone":[95],"AM,":[97,160],"well-structured":[100],"representations":[102],"given":[103],"alignment":[105,133,144],"(UA)":[106],"condition":[108],"during":[109],"training.":[110],"For":[111],"inference,":[113],"utilize":[115],"lexicon":[117],"to":[118,122,129,150,170,179],"map":[119],"input":[120],"text":[121],"phoneme":[124],"sequence,":[125],"expanded":[128],"frame-level":[131],"forced":[132],"(FA)":[134],"with":[135,181],"speaker-dependent":[137],"model.":[139],"Then,":[140],"develop":[142],"an":[143],"mapping":[145],"module":[146],"converts":[148],"FA":[149],"UA.":[151],"Finally,":[152],"C-DSVAE,":[154],"serving":[155],"takes":[161],"predicted":[163],"UA":[164],"target":[167],"speaker":[168],"embedding":[169],"generate":[171],"mel":[173],"spectrogram,":[174],"ultimately":[177],"converted":[178],"waveform":[180],"neural":[183],"vocoder.":[184],"show":[186],"how":[187],"method":[189],"enables":[190],"without":[193],"using":[194],"paired":[196],"corpus":[198],"AM":[200],"development":[201],"stage.":[202],"Experiments":[203],"demonstrate":[204],"can":[207],"synthesize":[208],"high":[211],"naturalness":[212],"intelligibility":[214],"measured":[215],"by":[216],"human":[217],"objective":[219],"evaluations.":[220],"Audio":[221],"samples":[222],"are":[223],"available":[224],"at":[225],"demo":[227],"page":[228]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-26T13:28:51.108037","created_date":"2023-06-29T00:00:00"}