{"id":"https://openalex.org/W2991267091","doi":"https://doi.org/10.1109/icassp40776.2020.9053678","title":"Using Vaes and Normalizing Flows for One-Shot Text-To-Speech Synthesis of Expressive Speech","display_name":"Using Vaes and Normalizing Flows for One-Shot Text-To-Speech Synthesis of Expressive Speech","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2991267091","doi":"https://doi.org/10.1109/icassp40776.2020.9053678","mag":"2991267091"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053678","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053678","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/1911.12760","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021819126","display_name":"Vatsal Aggarwal","orcid":"https://orcid.org/0000-0002-6477-1264"},"institutions":[{"id":"https://openalex.org/I4210123934","display_name":"Amazon (United Kingdom)","ror":"https://ror.org/02xey9634","country_code":"GB","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210123934"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vatsal Aggarwal","raw_affiliation_strings":["Amazon, Cambridge, UK","[Amazon, Cambridge, UK]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon, Cambridge, UK","institution_ids":["https://openalex.org/I4210123934"]},{"raw_affiliation_string":"[Amazon, Cambridge, UK]","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038640628","display_name":"Marius Cotescu","orcid":"https://orcid.org/0000-0001-7005-2920"},"institutions":[{"id":"https://openalex.org/I4210123934","display_name":"Amazon (United Kingdom)","ror":"https://ror.org/02xey9634","country_code":"GB","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210123934"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Marius Cotescu","raw_affiliation_strings":["Amazon, Cambridge, UK","[Amazon, Cambridge, UK]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon, Cambridge, UK","institution_ids":["https://openalex.org/I4210123934"]},{"raw_affiliation_string":"[Amazon, Cambridge, UK]","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078698588","display_name":"Nishant Prateek","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123934","display_name":"Amazon (United Kingdom)","ror":"https://ror.org/02xey9634","country_code":"GB","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210123934"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nishant Prateek","raw_affiliation_strings":["Amazon, Cambridge, UK","[Amazon, Cambridge, UK]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon, Cambridge, UK","institution_ids":["https://openalex.org/I4210123934"]},{"raw_affiliation_string":"[Amazon, Cambridge, UK]","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019530089","display_name":"Jaime Lorenzo-Trueba","orcid":"https://orcid.org/0000-0003-0459-1429"},"institutions":[{"id":"https://openalex.org/I4210123934","display_name":"Amazon (United Kingdom)","ror":"https://ror.org/02xey9634","country_code":"GB","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210123934"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jaime Lorenzo-Trueba","raw_affiliation_strings":["Amazon, Cambridge, UK","[Amazon, Cambridge, UK]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon, Cambridge, UK","institution_ids":["https://openalex.org/I4210123934"]},{"raw_affiliation_string":"[Amazon, Cambridge, UK]","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027755752","display_name":"Roberto Barra-Chicote","orcid":"https://orcid.org/0000-0003-0844-7037"},"institutions":[{"id":"https://openalex.org/I4210123934","display_name":"Amazon (United Kingdom)","ror":"https://ror.org/02xey9634","country_code":"GB","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210123934"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Roberto Barra-Chicote","raw_affiliation_strings":["Amazon, Cambridge, UK","[Amazon, Cambridge, UK]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon, Cambridge, UK","institution_ids":["https://openalex.org/I4210123934"]},{"raw_affiliation_string":"[Amazon, Cambridge, UK]","institution_ids":["https://openalex.org/I4210123934"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210123934"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6179","last_page":"6183"},"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/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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":0.9987999796867371,"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/naturalness","display_name":"Naturalness","score":0.9314353466033936},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7407383322715759},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7163503766059875},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7060362696647644},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6577582955360413},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5453559160232544},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5252796411514282},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5217186808586121},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.49172714352607727},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.47451868653297424},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4686759114265442},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4129675030708313},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3942524492740631},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35314297676086426},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.223939448595047},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1942213773727417},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13604506850242615},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12247389554977417}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.9314353466033936},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7407383322715759},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7163503766059875},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7060362696647644},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6577582955360413},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5453559160232544},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5252796411514282},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5217186808586121},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.49172714352607727},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.47451868653297424},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4686759114265442},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4129675030708313},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3942524492740631},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35314297676086426},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.223939448595047},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1942213773727417},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13604506850242615},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12247389554977417},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053678","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053678","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1911.12760","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.12760","pdf_url":"https://arxiv.org/pdf/1911.12760","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":null,"raw_type":"text"},{"id":"mag:2991267091","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1911.12760.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.1911.12760","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1911.12760","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"},{"id":"doi:10.17023/gxz2-6543","is_oa":true,"landing_page_url":"https://doi.org/10.17023/gxz2-6543","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1911.12760","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.12760","pdf_url":"https://arxiv.org/pdf/1911.12760","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":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2991267091.pdf","grobid_xml":"https://content.openalex.org/works/W2991267091.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W2527729766","https://openalex.org/W2559626456","https://openalex.org/W2788266530","https://openalex.org/W2793479148","https://openalex.org/W2795109282","https://openalex.org/W2795485067","https://openalex.org/W2889092828","https://openalex.org/W2899361462","https://openalex.org/W2901620353","https://openalex.org/W2941649920","https://openalex.org/W2949336561","https://openalex.org/W2949382160","https://openalex.org/W2951004968","https://openalex.org/W2954386831","https://openalex.org/W2962691331","https://openalex.org/W2963542120","https://openalex.org/W2963927338","https://openalex.org/W2964243274","https://openalex.org/W2972366998","https://openalex.org/W2973227003","https://openalex.org/W3177989406","https://openalex.org/W6640963894","https://openalex.org/W6730306933","https://openalex.org/W6748573829","https://openalex.org/W6752888775","https://openalex.org/W6755300632","https://openalex.org/W6756002706","https://openalex.org/W6936113694"],"related_works":["https://openalex.org/W2059721297","https://openalex.org/W3003284013","https://openalex.org/W2957723908","https://openalex.org/W1971670143","https://openalex.org/W2953719307","https://openalex.org/W3144639365","https://openalex.org/W2752161456","https://openalex.org/W3097301532","https://openalex.org/W2885800352","https://openalex.org/W2112974201","https://openalex.org/W2901611695","https://openalex.org/W2766406951","https://openalex.org/W2260501505","https://openalex.org/W2741633070","https://openalex.org/W2949836599","https://openalex.org/W3047107405","https://openalex.org/W2032233641","https://openalex.org/W2282712048","https://openalex.org/W3095755761","https://openalex.org/W3207354624"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,28,34,39,46,68,90,93],"Text-to-Speech":[3],"method":[4],"to":[5,71,111],"create":[6,89],"an":[7],"unseen":[8],"expressive":[9,15,65],"style":[10,66],"using":[11],"one":[12,19,62],"utterance":[13],"of":[14,17,27,64,114],"speech":[16],"around":[18],"second.":[20],"Specifically,":[21],"we":[22,60,87],"enhance":[23],"the":[24,72,79,105,112],"disentanglement":[25],"capabilities":[26],"state-of-the-art":[29],"sequence-to-sequence":[30],"based":[31],"system":[32,44],"with":[33,92],"Variational":[35],"AutoEncoder":[36],"(VAE)":[37],"and":[38],"Householder":[40],"Flow.":[41],"The":[42],"proposed":[43],"provides":[45],"22%":[47],"KL-divergence":[48],"reduction":[49],"while":[50,102],"jointly":[51],"improving":[52,104],"perceptual":[53],"metrics":[54],"over":[55,98],"state-of-the-art.":[56],"At":[57],"synthesis":[58],"time":[59],"use":[61],"example":[63],"as":[67],"reference":[69],"input":[70],"encoder":[73],"for":[74],"generating":[75],"any":[76],"text":[77],"in":[78],"desired":[80],"style.":[81],"Perceptual":[82],"MUSHRA":[83],"evaluations":[84],"show":[85],"that":[86],"can":[88],"voice":[91],"9%":[94],"relative":[95],"naturalness":[96],"improvement":[97],"standard":[99],"Neural":[100],"Text-to-Speech,":[101],"also":[103],"perceived":[106],"emotional":[107],"intensity":[108],"(59":[109],"compared":[110],"55":[113],"neutral":[115],"speech).":[116]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}