{"id":"https://openalex.org/W3168312215","doi":"https://doi.org/10.21437/interspeech.2021-562","title":"Improving Multi-Speaker TTS Prosody Variance with a Residual Encoder and Normalizing Flows","display_name":"Improving Multi-Speaker TTS Prosody Variance with a Residual Encoder and Normalizing Flows","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3168312215","doi":"https://doi.org/10.21437/interspeech.2021-562","mag":"3168312215"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-562","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-562","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2106.05762","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055920967","display_name":"Iv\u00e1n Vall\u00e9s-\u1e54erez","orcid":"https://orcid.org/0000-0002-7588-5777"},"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":"Iv\u00e1n Vall\u00e9s-P\u00e9rez","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053794772","display_name":"Julian Roth","orcid":null},"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":"Julian Roth","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045200344","display_name":"Grzegorz Beringer","orcid":null},"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":"Grzegorz Beringer","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027755752","display_name":"Roberto Barra-Chicote","orcid":"https://orcid.org/0000-0003-0844-7037"},"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":"Roberto Barra-Chicote","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012153296","display_name":"Jasha Droppo","orcid":"https://orcid.org/0000-0001-6097-0090"},"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":"Jasha Droppo","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":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07110425,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3131","last_page":"3135"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9993000030517578,"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":0.9979000091552734,"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/prosody","display_name":"Prosody","score":0.8605376482009888},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7772430777549744},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7061347961425781},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6571261882781982},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4551134705543518},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.4534979462623596},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35200053453445435},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34814611077308655}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8605376482009888},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7772430777549744},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7061347961425781},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6571261882781982},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4551134705543518},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.4534979462623596},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35200053453445435},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34814611077308655},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-562","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-562","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:2106.05762","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.05762","pdf_url":"https://arxiv.org/pdf/2106.05762","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3168312215","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2106.05762","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.2106.05762","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2106.05762","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2106.05762","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.05762","pdf_url":"https://arxiv.org/pdf/2106.05762","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3168312215.pdf","grobid_xml":"https://content.openalex.org/works/W3168312215.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W299440670","https://openalex.org/W1566256432","https://openalex.org/W2131774270","https://openalex.org/W2626778328","https://openalex.org/W2766272105","https://openalex.org/W2804664105","https://openalex.org/W2941531368","https://openalex.org/W2948978827","https://openalex.org/W2949335953","https://openalex.org/W2949382160","https://openalex.org/W2953343412","https://openalex.org/W2954386831","https://openalex.org/W2963139417","https://openalex.org/W2963609956","https://openalex.org/W2963927338","https://openalex.org/W2964243274","https://openalex.org/W2964308564","https://openalex.org/W3011246070","https://openalex.org/W3016151052","https://openalex.org/W3047107405","https://openalex.org/W3048768961","https://openalex.org/W3086296097","https://openalex.org/W3098557217"],"related_works":["https://openalex.org/W3197113339","https://openalex.org/W3166514188","https://openalex.org/W2292933197","https://openalex.org/W2591810795","https://openalex.org/W2121552713","https://openalex.org/W2088699022","https://openalex.org/W2101011209","https://openalex.org/W2963542120","https://openalex.org/W812778724","https://openalex.org/W2144294430","https://openalex.org/W2104117215","https://openalex.org/W2396822996","https://openalex.org/W2181384879","https://openalex.org/W88604210","https://openalex.org/W3171055158","https://openalex.org/W3202098869","https://openalex.org/W2069237452","https://openalex.org/W297015806","https://openalex.org/W2790551780","https://openalex.org/W2572696762"],"abstract_inverted_index":{"Text-to-speech":[0],"systems":[1,15,37,106],"recently":[2],"achieved":[3],"almost":[4],"indistinguishable":[5],"quality":[6],"from":[7],"human":[8],"speech.":[9],"However,":[10],"the":[11,57,72,84,89,93,97,124,141,148,159,162],"prosody":[12,32,121,131],"of":[13,28,105,129,161],"those":[14],"is":[16,33],"generally":[17],"flatter":[18],"than":[19,123],"natural":[20],"speech,":[21],"producing":[22,108],"samples":[23],"with":[24,75],"low":[25],"expressiveness.":[26],"Disentanglement":[27],"speaker":[29,67,137,142,150,155],"id":[30],"and":[31,42,69],"crucial":[34],"in":[35,102,126],"text-to-speech":[36,53],"to":[38,88],"improve":[39],"on":[40,65],"naturalness":[41],"produce":[43],"more":[44,109],"variable":[45],"syntheses.":[46],"This":[47],"paper":[48],"proposes":[49],"a":[50,62,76,127],"new":[51,77,116,163],"neural":[52],"model":[54,117],"that":[55,147],"approaches":[56],"disentanglement":[58],"problem":[59,99],"by":[60,70],"conditioning":[61],"Tacotron2-like":[63],"architecture":[64],"flow-normalized":[66],"embeddings,":[68],"substituting":[71],"reference":[73,94],"encoder":[74,95],"learned":[78],"latent":[79],"distribution":[80],"responsible":[81],"for":[82],"modeling":[83],"intra-sentence":[85],"variability":[86],"due":[87],"prosody.":[90],"By":[91],"removing":[92],"dependency,":[96],"speaker-leakage":[98],"typically":[100],"happening":[101],"this":[103],"kind":[104],"disappears,":[107],"distinctive":[110],"syntheses":[111],"at":[112],"inference":[113],"time.":[114],"The":[115],"achieves":[118],"significantly":[119],"higher":[120,136],"variance":[122],"baseline":[125],"set":[128],"quantitative":[130],"features,":[132],"as":[133,135],"well":[134],"distinctiveness,":[138],"without":[139],"decreasing":[140],"intelligibility.":[143],"Finally,":[144],"we":[145],"observe":[146],"normalized":[149],"embeddings":[151],"enable":[152],"much":[153],"richer":[154],"interpolations,":[156],"substantially":[157],"improving":[158],"distinctiveness":[160],"interpolated":[164],"speakers.":[165]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2022-07-25T00:00:00"}