{"id":"https://openalex.org/W3015282541","doi":"https://doi.org/10.1109/icassp40776.2020.9054484","title":"Flow-TTS: A Non-Autoregressive Network for Text to Speech Based on Flow","display_name":"Flow-TTS: A Non-Autoregressive Network for Text to Speech Based on Flow","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015282541","doi":"https://doi.org/10.1109/icassp40776.2020.9054484","mag":"3015282541"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054484","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5102412218","display_name":"Chenfeng Miao","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":true,"raw_author_name":"Chenfeng Miao","raw_affiliation_strings":["Ping An Technology"],"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033522290","display_name":"Shuang Liang","orcid":"https://orcid.org/0000-0001-7003-3906"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Shuang Liang","raw_affiliation_strings":["Ping An Technology"],"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059638789","display_name":"Minchuan Chen","orcid":"https://orcid.org/0009-0001-1512-6672"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Minchuan Chen","raw_affiliation_strings":["Ping An Technology"],"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100643103","display_name":"Jun Ma","orcid":"https://orcid.org/0009-0003-8713-0667"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Ma","raw_affiliation_strings":["Ping An Technology"],"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100702017","display_name":"Shaojun Wang","orcid":"https://orcid.org/0009-0001-8955-8566"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Shaojun Wang","raw_affiliation_strings":["Ping An Technology"],"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016038454","display_name":"Jing Xiao","orcid":"https://orcid.org/0000-0001-9615-4749"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Xiao","raw_affiliation_strings":["Ping An Technology"],"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102412218"],"corresponding_institution_ids":["https://openalex.org/I4401726822"],"apc_list":null,"apc_paid":null,"fwci":10.0123,"has_fulltext":false,"cited_by_count":93,"citation_normalized_percentile":{"value":0.98524884,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"2020","issue":null,"first_page":"7209","last_page":"7213"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"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/autoregressive-model","display_name":"Autoregressive model","score":0.893598198890686},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8559030294418335},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6975533962249756},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6694064140319824},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.5730830430984497},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5215756297111511},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5037280917167664},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4263409376144409},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3954159617424011},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13706538081169128},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07473233342170715}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.893598198890686},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8559030294418335},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6975533962249756},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6694064140319824},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.5730830430984497},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5215756297111511},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5037280917167664},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4263409376144409},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3954159617424011},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13706538081169128},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07473233342170715},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054484","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"mag:3185465848","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=202002246508106745","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","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":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1599623585","https://openalex.org/W2016589492","https://openalex.org/W2102003408","https://openalex.org/W2107860279","https://openalex.org/W2150658333","https://openalex.org/W2154920538","https://openalex.org/W2423557781","https://openalex.org/W2519091744","https://openalex.org/W2542835211","https://openalex.org/W2766812927","https://openalex.org/W2769810959","https://openalex.org/W2892140764","https://openalex.org/W2912298597","https://openalex.org/W2945613576","https://openalex.org/W2946200149","https://openalex.org/W2962695743","https://openalex.org/W2962882868","https://openalex.org/W2963091184","https://openalex.org/W2963139417","https://openalex.org/W2963300588","https://openalex.org/W2963403868","https://openalex.org/W2963609956","https://openalex.org/W2963636093","https://openalex.org/W2963782041","https://openalex.org/W2963975282","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W2970730223","https://openalex.org/W2972951102","https://openalex.org/W4289305009","https://openalex.org/W4289761690","https://openalex.org/W4294149591","https://openalex.org/W4294619240","https://openalex.org/W4297798428","https://openalex.org/W4298580827","https://openalex.org/W4385245566","https://openalex.org/W6714644935","https://openalex.org/W6728610325","https://openalex.org/W6739901393","https://openalex.org/W6745697700","https://openalex.org/W6748409065","https://openalex.org/W6752910514","https://openalex.org/W6753855596","https://openalex.org/W6754925833","https://openalex.org/W6756159577","https://openalex.org/W6758706709","https://openalex.org/W6763832098","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W2998781440","https://openalex.org/W127416991"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"propose":[4],"Flow-TTS,":[5],"a":[6,28,61,94],"non-autoregressive":[7,18],"end-to-end":[8],"neural":[9],"TTS":[10,39],"model":[11,40,51,87],"based":[12],"on":[13,65],"generative":[14],"flow.":[15],"Unlike":[16],"other":[17],"models,":[19],"Flow-TTS":[20,35,73,105],"can":[21],"achieve":[22],"high-quality":[23],"speech":[24,70],"generation":[25,45,59],"by":[26],"using":[27],"single":[29,62],"feed-forward":[30],"network.":[31,63],"To":[32],"our":[33],"knowledge,":[34],"is":[36,80,106,115],"the":[37,48,55,69,101],"first":[38,49],"utilizing":[41],"flow":[42],"in":[43,98],"spectrogram":[44,58],"network":[46],"and":[47,57,79],"non-autoregssive":[50],"which":[52,114],"jointly":[53],"learns":[54],"alignment":[56],"through":[60],"Experiments":[64],"LJSpeech":[66],"show":[67],"that":[68,76,84],"quality":[71],"of":[72,77,85,96,104],"heavily":[74],"approaches":[75],"human":[78],"even":[81],"better":[82],"than":[83],"autoregressive":[86],"Tacotron":[88,91,112],"2":[89,92],"(outperforms":[90],"with":[93],"gap":[95],"0.09":[97],"MOS).":[99],"Meanwhile,":[100],"inference":[102],"speed":[103],"about":[107],"23":[108],"times":[109],"speed-up":[110],"over":[111],"2,":[113],"comparable":[116],"to":[117],"FastSpeech.":[118],"<sup":[119],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[120],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[121]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":21},{"year":2022,"cited_by_count":25},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}