{"id":"https://openalex.org/W3169214411","doi":"https://doi.org/10.21437/interspeech.2021-528","title":"A Learned Conditional Prior for the VAE Acoustic Space of a TTS System","display_name":"A Learned Conditional Prior for the VAE Acoustic Space of a TTS System","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3169214411","doi":"https://doi.org/10.21437/interspeech.2021-528","mag":"3169214411"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-528","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-528","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2106.10229","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006537074","display_name":"Penny Karanasou","orcid":"https://orcid.org/0000-0003-1939-4161"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Penny Karanasou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066855316","display_name":"Sri Karlapati","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sri Karlapati","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014483986","display_name":"Alexis Moinet","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexis Moinet","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083043476","display_name":"Arnaud Joly","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arnaud Joly","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081086162","display_name":"Ammar Abbas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ammar Abbas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021062762","display_name":"Simon Slangen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simon Slangen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021990072","display_name":"Jaime Lorenzo Trueba","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaime Lorenzo-Trueba","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5029023520","display_name":"Thomas Drugman","orcid":"https://orcid.org/0000-0002-1491-7878"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Drugman","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3620","last_page":"3624"},"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":0.9990000128746033,"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/T10028","display_name":"Topic Modeling","score":0.9984999895095825,"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":0.5914610028266907},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5747998952865601},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5702981352806091},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5389912724494934},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.5006368160247803},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4801435172557831},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46525105834007263},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.45794859528541565},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.45641592144966125},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4216095209121704},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3639671802520752},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.2703537940979004},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24423393607139587},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.08807039260864258},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.06205400824546814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5914610028266907},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5747998952865601},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5702981352806091},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5389912724494934},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.5006368160247803},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4801435172557831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46525105834007263},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.45794859528541565},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.45641592144966125},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4216095209121704},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3639671802520752},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2703537940979004},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24423393607139587},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.08807039260864258},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.06205400824546814},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-528","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-528","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"},{"id":"pmh:oai:arXiv.org:2106.10229","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.10229","pdf_url":"https://arxiv.org/pdf/2106.10229","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3169214411","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2106.10229.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2106.10229","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2106.10229","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2106.10229","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.10229","pdf_url":"https://arxiv.org/pdf/2106.10229","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3169214411.pdf","grobid_xml":"https://content.openalex.org/works/W3169214411.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2187089797","https://openalex.org/W2188365844","https://openalex.org/W2532494225","https://openalex.org/W2556467266","https://openalex.org/W2904459034","https://openalex.org/W2962691331","https://openalex.org/W2962738009","https://openalex.org/W2962788625","https://openalex.org/W2962850167","https://openalex.org/W2963223306","https://openalex.org/W2963272440","https://openalex.org/W2963568578","https://openalex.org/W2963609956","https://openalex.org/W2963927338","https://openalex.org/W2964243274","https://openalex.org/W2990883660","https://openalex.org/W3026278778","https://openalex.org/W3095491807","https://openalex.org/W3097320728","https://openalex.org/W3161732385","https://openalex.org/W3203206590"],"related_works":["https://openalex.org/W2977881783","https://openalex.org/W2890868349","https://openalex.org/W2891566965","https://openalex.org/W2957959342","https://openalex.org/W2987099509","https://openalex.org/W2799037524","https://openalex.org/W2901123912","https://openalex.org/W2250174980","https://openalex.org/W2786243250","https://openalex.org/W2161462756","https://openalex.org/W2398584126","https://openalex.org/W2742098066","https://openalex.org/W2609714908","https://openalex.org/W2157283201","https://openalex.org/W832071521","https://openalex.org/W2004887172","https://openalex.org/W2738734060","https://openalex.org/W2964548769","https://openalex.org/W2574767818","https://openalex.org/W2805334656"],"abstract_inverted_index":{"Many":[0],"factors":[1],"influence":[2],"speech":[3],"yielding":[4],"different":[5],"renditions":[6,24],"of":[7,25,33,64,96,128,144,156,175],"a":[8,51,65,97,104,125],"given":[9],"sentence.":[10],"Generative":[11],"models,":[12],"such":[13],"as":[14,91,165,167],"variational":[15],"autoencoders":[16],"(VAEs),":[17],"capture":[18],"this":[19,47],"variability":[20,35],"and":[21,120],"allow":[22],"multiple":[23],"the":[26,39,60,85,93,111,116,129,145,157,173,176],"same":[27],"sentence":[28],"via":[29],"sampling.":[30,45],"The":[31],"degree":[32],"prosodic":[34,79],"depends":[36],"heavily":[37],"on":[38,103],"prior":[40,58,92],"that":[41],"is":[42],"used":[43],"when":[44],"In":[46],"paper,":[48],"we":[49,73,101,107],"propose":[50],"novel":[52],"method":[53],"to":[54,75,170],"compute":[55],"an":[56],"informative":[57],"for":[59,132],"VAE":[61,113],"latent":[62,86,130,158],"space":[63,131,159],"neural":[66],"text-to-speech":[67],"(TTS)":[68],"system.":[69,177],"By":[70,89],"doing":[71],"so,":[72],"aim":[74],"sample":[76,109],"with":[77],"more":[78],"variability,":[80],"while":[81],"gaining":[82],"controllability":[83],"over":[84,148],"space's":[87],"structure.":[88],"using":[90],"posterior":[94],"distribution":[95],"secondary":[98],"VAE,":[99],"which":[100],"condition":[102,134],"speaker":[105],"vector,":[106],"can":[108],"from":[110,124],"primary":[112],"taking":[114],"explicitly":[115],"conditioning":[117],"into":[118],"account":[119],"resulting":[121],"in":[122],"samples":[123],"specific":[126],"region":[127],"each":[133],"(i.e.":[135],"speaker).":[136],"A":[137],"formal":[138],"preference":[139,143],"test":[140],"demonstrates":[141],"significant":[142],"proposed":[146],"approach":[147],"standard":[149],"Conditional":[150],"VAE.":[151],"We":[152],"also":[153],"provide":[154],"visualisations":[155],"where":[160],"well-separated":[161],"condition-specific":[162],"clusters":[163],"appear,":[164],"well":[166],"ablation":[168],"studies":[169],"better":[171],"understand":[172],"behaviour":[174]},"counts_by_year":[{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}