{"id":"https://openalex.org/W3168520256","doi":"https://doi.org/10.21437/interspeech.2021-1555","title":"Improving the Expressiveness of Neural Vocoding with Non-Affine Normalizing Flows","display_name":"Improving the Expressiveness of Neural Vocoding with Non-Affine Normalizing Flows","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3168520256","doi":"https://doi.org/10.21437/interspeech.2021-1555","mag":"3168520256"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1555","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1555","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":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2106.08649.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031116817","display_name":"Adam Gabry\u015b","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adam Gabry\u015b","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062423359","display_name":"Yunlong Jiao","orcid":"https://orcid.org/0000-0002-0776-0550"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunlong Jiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026578737","display_name":"Viacheslav Klimkov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Viacheslav Klimkov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039620116","display_name":"Daniel Korzekwa","orcid":"https://orcid.org/0000-0003-1470-4968"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Korzekwa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"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/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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05869544,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1679","last_page":"1683"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9994999766349792,"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/T10320","display_name":"Neural Networks and Applications","score":0.9994999766349792,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983000159263611,"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/affine-transformation","display_name":"Affine transformation","score":0.7715810537338257},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7464309930801392},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.593902587890625},{"id":"https://openalex.org/keywords/invertible-matrix","display_name":"Invertible matrix","score":0.5410711765289307},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46151185035705566},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.44753196835517883},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41963380575180054},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3606454133987427},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33975574374198914},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.288754940032959},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.11014661192893982},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07666900753974915}],"concepts":[{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.7715810537338257},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7464309930801392},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.593902587890625},{"id":"https://openalex.org/C96442724","wikidata":"https://www.wikidata.org/wiki/Q242188","display_name":"Invertible matrix","level":2,"score":0.5410711765289307},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46151185035705566},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.44753196835517883},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41963380575180054},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3606454133987427},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33975574374198914},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.288754940032959},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.11014661192893982},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07666900753974915},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2021-1555","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1555","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":"mag:3168520256","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2106.08649.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2106.08649","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2106.08649","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"article-journal"}],"best_oa_location":{"id":"mag:3168520256","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2106.08649.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W2077811453","https://openalex.org/W2423557781","https://openalex.org/W2431962807","https://openalex.org/W2519091744","https://openalex.org/W2593729559","https://openalex.org/W2604184139","https://openalex.org/W2899882692","https://openalex.org/W2912298597","https://openalex.org/W2946795888","https://openalex.org/W2948211236","https://openalex.org/W2948613292","https://openalex.org/W2948659923","https://openalex.org/W2948700496","https://openalex.org/W2951004968","https://openalex.org/W2963091184","https://openalex.org/W2963139417","https://openalex.org/W2963300588","https://openalex.org/W2963540976","https://openalex.org/W2963782041","https://openalex.org/W2963975282","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W2964343746","https://openalex.org/W2965107313","https://openalex.org/W2969446490","https://openalex.org/W2970006822","https://openalex.org/W2979652999","https://openalex.org/W2992005611","https://openalex.org/W2992035660","https://openalex.org/W3015338123","https://openalex.org/W3015611309","https://openalex.org/W3033752673","https://openalex.org/W3092028330","https://openalex.org/W3114951884","https://openalex.org/W3161236344","https://openalex.org/W3162770051"],"related_works":["https://openalex.org/W2954882728","https://openalex.org/W3211889635","https://openalex.org/W2594927458","https://openalex.org/W3093733783","https://openalex.org/W2968397919","https://openalex.org/W3198104520","https://openalex.org/W2945993525","https://openalex.org/W2994785103","https://openalex.org/W3112470437","https://openalex.org/W2800664709","https://openalex.org/W2949756029","https://openalex.org/W3003901600","https://openalex.org/W3163521645","https://openalex.org/W3164680725","https://openalex.org/W2963103134","https://openalex.org/W3181138750","https://openalex.org/W3163677684","https://openalex.org/W2471883461","https://openalex.org/W3004402693","https://openalex.org/W2952917250"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,16,25,78],"general":[4],"enhancement":[5],"to":[6,33,40,55,101,140],"the":[7,35,41,51,62,71,83,87,91,98,124,141,147,154],"Normalizing":[8],"Flows":[9],"(NF)":[10],"used":[11],"in":[12,61,120],"neural":[13,109],"vocoding.":[14],"As":[15],"case":[17],"study,":[18],"we":[19,31,145],"improve":[20],"expressive":[21,43],"speech":[22],"vocoding":[23,110],"with":[24,128,162],"revamped":[26],"Parallel":[27],"Wavenet":[28],"(PW).":[29],"Specifically,":[30],"propose":[32],"extend":[34,146],"affine":[36,142],"transformation":[37],"of":[38,50],"PW":[39,53,100,156],"more":[42,113],"invertible":[44,165],"non-affine":[45,164],"function.":[46,168],"The":[47],"greater":[48],"expressiveness":[49],"improved":[52],"leads":[54],"better-perceived":[56],"signal":[57,94],"quality":[58,95],"and":[59,65,93,105,132,137,166],"naturalness":[60,92],"waveform":[63,84],"reconstruction":[64,85],"text-to-speech":[66],"(TTS)":[67],"tasks.":[68],"We":[69,116],"evaluate":[70],"model":[72,89],"across":[73],"different":[74],"speaking":[75],"styles":[76],"on":[77,123],"multi-speaker,":[79],"multi-lingual":[80],"dataset.":[81],"In":[82],"task,":[86],"proposed":[88,152],"closes":[90],"gap":[96],"from":[97,106],"original":[99,155],"recordings":[102],"by":[103,112,135,153],"$10\\%$,":[104],"other":[107],"state-of-the-art":[108],"systems":[111],"than":[114],"$60\\%$.":[115],"also":[117],"demonstrate":[118],"improvements":[119],"objective":[121],"metrics":[122],"evaluation":[125],"test":[126],"set":[127],"L2":[129],"Spectral":[130],"Distance":[131],"Cross-Entropy":[133],"reduced":[134],"$3\\%$":[136],"$6\\unicode{x2030}$":[138],"comparing":[139],"PW.":[143],"Furthermore,":[144],"probability":[148],"density":[149],"distillation":[150],"procedure":[151],"paper,":[157],"so":[158],"that":[159],"it":[160],"works":[161],"any":[163],"differentiable":[167]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}