{"id":"https://openalex.org/W4224928632","doi":"https://doi.org/10.1109/icassp43922.2022.9747050","title":"Varianceflow: High-Quality and Controllable Text-to-Speech using Variance Information via Normalizing Flow","display_name":"Varianceflow: High-Quality and Controllable Text-to-Speech using Variance Information via Normalizing Flow","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224928632","doi":"https://doi.org/10.1109/icassp43922.2022.9747050"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747050","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2302.13458","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045637107","display_name":"Yoonhyung Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Yoonhyung Lee","raw_affiliation_strings":["Seoul National University,Dept. of Electrical and Computer Engineering,Republic of Korea","Dept. of Electrical and Computer Engineering, Seoul National University, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Dept. of Electrical and Computer Engineering,Republic of Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, Seoul National University, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073217180","display_name":"Jinhyeok Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135449","display_name":"NCSOFT (South Korea)","ror":"https://ror.org/03q4mza74","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210135449"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jinhyeok Yang","raw_affiliation_strings":["Speech AI Lab, NCSOFT,Republic of Korea","Speech AI Lab, NCSOFT, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Speech AI Lab, NCSOFT,Republic of Korea","institution_ids":["https://openalex.org/I4210135449"]},{"raw_affiliation_string":"Speech AI Lab, NCSOFT, Republic of Korea","institution_ids":["https://openalex.org/I4210135449"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077832834","display_name":"Kyomin Jung","orcid":"https://orcid.org/0000-0003-2547-7051"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyomin Jung","raw_affiliation_strings":["Seoul National University,Dept. of Electrical and Computer Engineering,Republic of Korea","Dept. of Electrical and Computer Engineering, Seoul National University, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Dept. of Electrical and Computer Engineering,Republic of Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, Seoul National University, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5045637107"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.105,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.24385202,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"33","issue":null,"first_page":"7477","last_page":"7481"},"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/variance","display_name":"Variance (accounting)","score":0.807845413684845},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7247734665870667},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.6395936012268066},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5868436098098755},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5281367897987366},{"id":"https://openalex.org/keywords/information-flow","display_name":"Information flow","score":0.5097405314445496},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4726875126361847},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35867857933044434},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2025311291217804},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.20076709985733032}],"concepts":[{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.807845413684845},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7247734665870667},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.6395936012268066},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5868436098098755},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5281367897987366},{"id":"https://openalex.org/C2779136372","wikidata":"https://www.wikidata.org/wiki/Q10283002","display_name":"Information flow","level":2,"score":0.5097405314445496},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4726875126361847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35867857933044434},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2025311291217804},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.20076709985733032},{"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},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747050","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2302.13458","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.13458","pdf_url":"https://arxiv.org/pdf/2302.13458","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2302.13458","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.13458","pdf_url":"https://arxiv.org/pdf/2302.13458","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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4224928632.pdf"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1583912456","https://openalex.org/W2107740512","https://openalex.org/W2884225676","https://openalex.org/W2903739847","https://openalex.org/W2908510526","https://openalex.org/W2946200149","https://openalex.org/W2964243274","https://openalex.org/W3025528898","https://openalex.org/W3026874504","https://openalex.org/W3033411150","https://openalex.org/W3034949308","https://openalex.org/W3038172701","https://openalex.org/W3092028330","https://openalex.org/W3150572638","https://openalex.org/W3169905056","https://openalex.org/W3172148458","https://openalex.org/W3196308991","https://openalex.org/W3197541421","https://openalex.org/W4287111234","https://openalex.org/W4287111656","https://openalex.org/W4287121924","https://openalex.org/W4297798428","https://openalex.org/W4297813370","https://openalex.org/W4385245566","https://openalex.org/W6635084905","https://openalex.org/W6714644935","https://openalex.org/W6739901393","https://openalex.org/W6757817989","https://openalex.org/W6763486065","https://openalex.org/W6763832098","https://openalex.org/W6777694618","https://openalex.org/W6778083308","https://openalex.org/W6778823374","https://openalex.org/W6779871621","https://openalex.org/W6783867762","https://openalex.org/W6785102375","https://openalex.org/W6795261426","https://openalex.org/W6796464841","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2036697162","https://openalex.org/W2332386680","https://openalex.org/W2561315646","https://openalex.org/W2248621902","https://openalex.org/W2003779889","https://openalex.org/W4205698120","https://openalex.org/W4239246781","https://openalex.org/W2164760767","https://openalex.org/W2542825942","https://openalex.org/W3201620972"],"abstract_inverted_index":{"There":[0],"are":[1],"two":[2,89],"types":[3],"of":[4,87,112,148],"methods":[5],"for":[6],"non-autoregressive":[7],"text-to-speech":[8],"models":[9,144],"to":[10,24,39,60,71],"learn":[11],"the":[12,53,62,67,85,88,93,99,109,115,118,122],"one-to-many":[13],"relationship":[14],"between":[15],"text":[16,123],"and":[17,121,151],"speech":[18,106,149],"effectively.":[19],"The":[20,35],"first":[21],"one":[22,37],"is":[23,38,57],"use":[25,40,117],"an":[26],"advanced":[27],"generative":[28],"framework":[29],"such":[30,43],"as":[31,44],"normalizing":[32],"flow":[33],"(NF).":[34],"second":[36,54],"variance":[41,63,68,94,100,119,132],"information":[42,101,120],"pitch":[45],"or":[46],"energy":[47],"together":[48],"when":[49],"generating":[50],"speech.":[51],"For":[52],"type,":[55],"it":[56],"also":[58],"possible":[59],"control":[61],"factors":[64],"by":[65],"adjusting":[66],"values":[69],"provided":[70],"a":[72,79,125],"model.":[73],"In":[74,134],"this":[75],"paper,":[76],"we":[77],"propose":[78],"novel":[80],"model":[81,116],"called":[82],"VarianceFlow":[83,97,136],"combining":[84],"advantages":[86],"types.":[90],"By":[91],"modeling":[92],"with":[95,104],"NF,":[96],"predicts":[98],"more":[102,130],"precisely":[103],"improved":[105],"quality.":[107],"Also,":[108],"objective":[110],"function":[111],"NF":[113],"makes":[114],"in":[124,129,146],"disentangled":[126],"manner":[127],"resulting":[128],"precise":[131],"control.":[133],"experiments,":[135],"shows":[137],"superior":[138],"performance":[139],"over":[140],"other":[141],"state-of-the-art":[142],"TTS":[143],"both":[145],"terms":[147],"quality":[150],"controllability.":[152]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}