{"id":"https://openalex.org/W4372266930","doi":"https://doi.org/10.1109/icassp49357.2023.10095301","title":"AE-Flow: Autoencoder Normalizing Flow","display_name":"AE-Flow: Autoencoder Normalizing Flow","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266930","doi":"https://doi.org/10.1109/icassp49357.2023.10095301"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095301","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5027787894","display_name":"Jakub Mosi\u0144ski","orcid":"https://orcid.org/0009-0007-7259-9613"},"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":"Jakub Mosi\u0144ski","raw_affiliation_strings":["Amazon Alexa AI"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","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":false,"raw_author_name":"Piotr Bili\u0144ski","raw_affiliation_strings":["Amazon Alexa AI"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","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 AI"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","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 AI"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","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 AI"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5027787894"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":0.7042,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74848555,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9991999864578247,"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/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.8517880439758301},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6545668244361877},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6223990321159363},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5653369426727295},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5158740282058716},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5059329867362976},{"id":"https://openalex.org/keywords/identifiability","display_name":"Identifiability","score":0.45865628123283386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41560399532318115},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3509330153465271},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.31399446725845337},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.27769941091537476},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.19338184595108032}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8517880439758301},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6545668244361877},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6223990321159363},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5653369426727295},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5158740282058716},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5059329867362976},{"id":"https://openalex.org/C122770356","wikidata":"https://www.wikidata.org/wiki/Q1656753","display_name":"Identifiability","level":2,"score":0.45865628123283386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41560399532318115},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3509330153465271},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.31399446725845337},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.27769941091537476},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19338184595108032},{"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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095301","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W142801778","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W2118850452","https://openalex.org/W2153057929","https://openalex.org/W2576309025","https://openalex.org/W2912298597","https://openalex.org/W2947196194","https://openalex.org/W2962788625","https://openalex.org/W2963035245","https://openalex.org/W2992005611","https://openalex.org/W3015282541","https://openalex.org/W3022876224","https://openalex.org/W3025528898","https://openalex.org/W3026874504","https://openalex.org/W3098557217","https://openalex.org/W3162770051","https://openalex.org/W3195171908","https://openalex.org/W3196584150","https://openalex.org/W4225316945","https://openalex.org/W4288337064","https://openalex.org/W4289761690","https://openalex.org/W4295312788","https://openalex.org/W4296069283","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6752910514","https://openalex.org/W6758706709","https://openalex.org/W6766978945","https://openalex.org/W6770970757","https://openalex.org/W6777694618","https://openalex.org/W6778083308","https://openalex.org/W6781662123"],"related_works":["https://openalex.org/W2081919107","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/W4400309480","https://openalex.org/W2549308614","https://openalex.org/W2023694213"],"abstract_inverted_index":{"Recently":[0],"normalizing":[1,37,99,177],"flows":[2,21,100],"have":[3],"been":[4],"gaining":[5],"traction":[6],"in":[7,97,143,150],"text-to-speech":[8],"(TTS)":[9],"and":[10,83,93,120,152,168,188],"voice":[11],"conversion":[12],"(VC)":[13],"due":[14],"to":[15,32,62,68,76,172],"their":[16],"state-of-the-art":[17],"(SOTA)":[18],"performance.":[19],"Normalizing":[20,51],"are":[22,141],"unsupervised":[23],"generative":[24],"models.":[25],"In":[26],"this":[27,47],"paper,":[28],"we":[29,107,131,180],"introduce":[30],"supervision":[31],"the":[33,40,60,66,78,85,89,94,160,191],"training":[34,48,98,162,174],"process":[35],"of":[36,80,88,145,176],"flows,":[38],"without":[39],"need":[41],"for":[42],"parallel":[43],"data.":[44],"We":[45],"call":[46],"paradigm":[49,163],"AutoEncoder":[50],"Flow":[52],"(AE-Flow).":[53],"It":[54],"adds":[55],"a":[56],"reconstruction":[57,95,121,127],"loss":[58,96,128],"forcing":[59],"model":[61,112,134],"use":[63],"information":[64],"from":[65],"conditioning":[67],"reconstruct":[69],"an":[70],"audio":[71],"sample.":[72],"Our":[73],"goal":[74],"is":[75],"understand":[77],"impact":[79],"each":[81],"component":[82],"find":[84],"right":[86],"combination":[87],"negative":[90],"log-likelihood":[91],"(NLL)":[92],"with":[101,135],"coupling":[102],"blocks.":[103],"For":[104],"that":[105,159,182],"reason":[106],"will":[108],"compare":[109,132],"flow-based":[110],"mapping":[111],"trained":[113],"with:":[114],"(i)":[115],"NLL":[116,119],"loss,":[117],"(ii)":[118],"losses,":[122],"as":[123,125],"well":[124],"(iii)":[126],"only.":[129],"Additionally,":[130],"our":[133,183],"SOTA":[136],"VC":[137,154],"baseline.":[138],"The":[139,156],"models":[140],"evaluated":[142],"terms":[144],"naturalness,":[146],"speaker":[147,166,186],"similarity,":[148],"intelligibility":[149,189],"many-to-many":[151],"many-to-any":[153],"settings.":[155],"results":[157],"show":[158,181],"proposed":[161],"systematically":[164],"improves":[165,185],"similarity":[167,187],"naturalness":[169],"when":[170],"compared":[171],"regular":[173],"methods":[175],"flows.":[178],"Furthermore,":[179],"method":[184],"over":[190],"state-of-the-art.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}