{"id":"https://openalex.org/W4296069283","doi":"https://doi.org/10.21437/interspeech.2022-10195","title":"Creating New Voices using Normalizing Flows","display_name":"Creating New Voices using Normalizing Flows","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296069283","doi":"https://doi.org/10.21437/interspeech.2022-10195"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10195","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10195","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2312.14569","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060480943","display_name":"Piotr Bili\u0144ski","orcid":"https://orcid.org/0000-0002-7023-3438"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Piotr Bilinski","raw_affiliation_strings":["Amazon Alexa"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038417409","display_name":"Thomas Merritt","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Merritt","raw_affiliation_strings":["Amazon Alexa"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027412678","display_name":"Abdelhamid Ezzerg","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdelhamid Ezzerg","raw_affiliation_strings":["Amazon Alexa"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000904701","display_name":"Kamil Pokora","orcid":"https://orcid.org/0009-0006-0756-4118"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kamil Pokora","raw_affiliation_strings":["Amazon Alexa"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069232913","display_name":"Sebastian Cygert","orcid":"https://orcid.org/0000-0002-4763-8381"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sebastian Cygert","raw_affiliation_strings":["Amazon Alexa"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047287498","display_name":"Kayoko Yanagisawa","orcid":"https://orcid.org/0000-0002-3444-7287"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kayoko Yanagisawa","raw_affiliation_strings":["Amazon Alexa"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"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/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roberto Barra-Chicote","raw_affiliation_strings":["Amazon Alexa"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039620116","display_name":"Daniel Korzekwa","orcid":"https://orcid.org/0000-0003-1470-4968"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Korzekwa","raw_affiliation_strings":["Amazon Alexa"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5060480943"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":1.0471,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.78719457,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2958","last_page":"2962"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6238999962806702,"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":0.6238999962806702,"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/T11448","display_name":"Face recognition and analysis","score":0.05779999867081642,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.03880000114440918,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8275056481361389},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7777417898178101},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6068698167800903},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6056671738624573},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5960143804550171},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5626398324966431},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.45993804931640625},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4597582519054413},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4403313100337982},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3856394290924072},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34706974029541016},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.09810414910316467}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8275056481361389},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7777417898178101},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6068698167800903},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6056671738624573},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5960143804550171},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5626398324966431},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.45993804931640625},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4597582519054413},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4403313100337982},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3856394290924072},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34706974029541016},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.09810414910316467},{"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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},{"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2022-10195","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10195","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2312.14569","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.14569","pdf_url":"https://arxiv.org/pdf/2312.14569","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2312.14569","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.14569","pdf_url":"https://arxiv.org/pdf/2312.14569","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":[{"id":"https://metadata.un.org/sdg/10","score":0.46000000834465027,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4296069283.pdf","grobid_xml":"https://content.openalex.org/works/W4296069283.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W2094721231","https://openalex.org/W2153057929","https://openalex.org/W2912298597","https://openalex.org/W2945478979","https://openalex.org/W2946200149","https://openalex.org/W2963300588","https://openalex.org/W2963654953","https://openalex.org/W2964243274","https://openalex.org/W2992005611","https://openalex.org/W3015282541","https://openalex.org/W3022876224","https://openalex.org/W3025528898","https://openalex.org/W3026874504","https://openalex.org/W3033411150","https://openalex.org/W3091928890","https://openalex.org/W3141898517","https://openalex.org/W3161492781","https://openalex.org/W3162046328","https://openalex.org/W3162770051","https://openalex.org/W3194822862","https://openalex.org/W3195171908","https://openalex.org/W3196584150","https://openalex.org/W4226105991","https://openalex.org/W4288337064","https://openalex.org/W4294619240","https://openalex.org/W4399584083"],"related_works":["https://openalex.org/W2079655441","https://openalex.org/W2912293245","https://openalex.org/W4252942110","https://openalex.org/W1604114751","https://openalex.org/W2032941915","https://openalex.org/W2075706796","https://openalex.org/W2549308614","https://openalex.org/W2023694213","https://openalex.org/W4377694462","https://openalex.org/W2081919107"],"abstract_inverted_index":{"Creating":[0],"realistic":[1],"and":[2,38,62,64,71,80,90,102,156,182,190,195],"natural-sounding":[3],"synthetic":[4],"speech":[5,105,154],"remains":[6],"a":[7,187],"big":[8],"challenge":[9],"for":[10,60],"voice":[11,39,104],"identities":[12],"unseen":[13,52,123],"during":[14,48],"training.":[15],"As":[16],"there":[17],"is":[18,113,130],"growing":[19],"interest":[20],"in":[21,35,73,152,162],"synthesizing":[22],"voices":[23,178],"of":[24,32,75,109,118,127,192],"new":[25,84,103,137,159,177],"speakers,":[26],"here":[27],"we":[28,56,66],"investigate":[29],"the":[30,110,116,119,128,133,143,163,172,193],"ability":[31,81,134],"normalizing":[33,183],"flows":[34],"text-to-speech":[36],"(TTS)":[37],"conversion":[40,120],"(VC)":[41],"modes":[42],"to":[43,50,82,93,114,121,131,135,148,170,175],"extrapolate":[44],"from":[45],"speakers":[46],"observed":[47],"training":[49,164],"create":[51,57,83,136],"speaker":[53,78],"identities.":[54],"Firstly,":[55],"an":[58,122],"approach":[59,145],"TTS":[61,194],"VC,":[63],"then":[65],"comprehensively":[67],"evaluate":[68],"our":[69,95],"methods":[70],"baselines":[72],"terms":[74],"intelligibility,":[76],"naturalness,":[77],"similarity,":[79],"voices.":[85,138],"We":[86,166],"use":[87],"both":[88],"objective":[89],"subjective":[91],"metrics":[92],"benchmark":[94],"techniques":[96],"on":[97,180],"2":[98],"evaluation":[99],"tasks:":[100],"zero-shot":[101,153],"synthesis.":[106],"The":[107,125],"goal":[108,126],"former":[111],"task":[112],"measure":[115,132],"precision":[117],"voice.":[124],"latter":[129],"Extensive":[139],"evaluations":[140],"demonstrate":[141],"that":[142],"proposed":[144],"systematically":[146],"allows":[147],"obtain":[149],"state-of-the-art":[150],"performance":[151],"synthesis":[155],"creates":[157],"various":[158],"voices,":[160],"unobserved":[161],"set.":[165],"consider":[167],"this":[168],"work":[169],"be":[171],"first":[173],"attempt":[174],"synthesize":[176],"based":[179],"mel-spectrograms":[181],"flows,":[184],"along":[185],"with":[186],"comprehensive":[188],"analysis":[189],"comparison":[191],"VC":[196],"modes.":[197]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}