{"id":"https://openalex.org/W3204679573","doi":"https://doi.org/10.21437/interspeech.2022-272","title":"FlowVocoder: A small Footprint Neural Vocoder based Normalizing Flow for Speech Synthesis","display_name":"FlowVocoder: A small Footprint Neural Vocoder based Normalizing Flow for Speech Synthesis","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W3204679573","doi":"https://doi.org/10.21437/interspeech.2022-272","mag":"3204679573"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-272","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-272","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":["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/A5049516896","display_name":"Manh Luong","orcid":"https://orcid.org/0000-0003-2754-4609"},"institutions":[{"id":"https://openalex.org/I4403386605","display_name":"PRX Research","ror":"https://ror.org/03f0sw771","country_code":null,"type":"facility","lineage":["https://openalex.org/I4403386605"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Manh Luong","raw_affiliation_strings":["Deezer Research and Development"],"affiliations":[{"raw_affiliation_string":"Deezer Research and Development","institution_ids":["https://openalex.org/I4403386605"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109521033","display_name":"Viet Anh Tran","orcid":null},"institutions":[{"id":"https://openalex.org/I4403386605","display_name":"PRX Research","ror":"https://ror.org/03f0sw771","country_code":null,"type":"facility","lineage":["https://openalex.org/I4403386605"]}],"countries":[],"is_corresponding":true,"raw_author_name":"Viet Anh Tran","raw_affiliation_strings":["Deezer Research and Development"],"affiliations":[{"raw_affiliation_string":"Deezer Research and Development","institution_ids":["https://openalex.org/I4403386605"]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5109521033"],"corresponding_institution_ids":["https://openalex.org/I4403386605"],"apc_list":null,"apc_paid":null,"fwci":0.1039,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.22112691,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1576","last_page":"1580"},"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":0.9994999766349792,"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":0.9962999820709229,"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/computer-science","display_name":"Computer science","score":0.7483691573143005},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7151066064834595},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.6827239394187927},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4481378197669983},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4133136570453644},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2634466886520386},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.07299408316612244}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7483691573143005},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7151066064834595},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.6827239394187927},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4481378197669983},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4133136570453644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2634466886520386},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.07299408316612244},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-272","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-272","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2107860279","https://openalex.org/W2120847449","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2786868129","https://openalex.org/W2894295011","https://openalex.org/W2912298597","https://openalex.org/W2962882868","https://openalex.org/W2963300588","https://openalex.org/W2963975282","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W2972597685","https://openalex.org/W2993118648","https://openalex.org/W2996286887","https://openalex.org/W3015338123","https://openalex.org/W3021066808","https://openalex.org/W3035068567","https://openalex.org/W3035289074","https://openalex.org/W3092028330","https://openalex.org/W3098403858","https://openalex.org/W3104674435","https://openalex.org/W3144035034","https://openalex.org/W3161236344","https://openalex.org/W3197273793","https://openalex.org/W4289305009","https://openalex.org/W4294619240","https://openalex.org/W4297817572"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W127416991"],"abstract_inverted_index":{"Recently,":[0],"autoregressive":[1,22,58,76],"neural":[2,23,59,77],"vocoders":[3,24],"have":[4,13],"provided":[5],"remarkable":[6],"performance":[7,62],"in":[8,20,94,136,145],"generating":[9,91],"high-fidelity":[10,92],"speech":[11,19],"and":[12,87,150],"been":[14],"able":[15],"to":[16,42],"produce":[17],"synthetic":[18],"real-time.However,":[21],"such":[25],"as":[26],"WaveFlow":[27],"are":[28],"capable":[29,89,121],"of":[30,38,53,63,75,90,102,109,122,147],"modeling":[31,123],"waveform":[32,124],"signals":[33],"from":[34],"mel-spectrogram,":[35],"its":[36,127],"number":[37,52],"parameters":[39],"is":[40,55,65,88,120,130,155],"significant":[41],"deploy":[43],"on":[44],"edge":[45],"devices.Though":[46],"NanoFlow,":[47],"which":[48,81],"has":[49,82],"a":[50,56,72,83,107],"small":[51,84],"parameters,":[54],"state-of-the-art":[57],"vocoder,":[60],"the":[61,99,117],"NanoFlow":[64],"marginally":[66],"lower":[67],"than":[68,133],"WaveFlow.Therefore,":[69],"we":[70],"propose":[71],"new":[73],"type":[74],"vocoder":[78],"called":[79],"FlowVocoder,":[80],"memory":[85,128],"footprint":[86,129],"audio":[93],"realtime.Our":[95],"proposed":[96,118],"model":[97,119],"improves":[98],"density":[100],"estimation":[101],"flow":[103],"blocks":[104],"by":[105],"utilizing":[106],"mixture":[108],"Cumulative":[110],"Distribution":[111],"Functions":[112],"(CDF)":[113],"for":[114,158],"bipartite":[115],"transformation.Hence,":[116],"signals,":[125],"while":[126],"much":[131],"smaller":[132],"WaveFlow.As":[134],"shown":[135],"experiments,":[137],"FlowVocoder":[138],"achieves":[139],"competitive":[140],"results":[141],"with":[142],"baseline":[143],"methods":[144],"terms":[146],"both":[148],"subjective":[149],"objective":[151],"evaluation,":[152],"also,":[153],"it":[154],"more":[156],"suitable":[157],"real-time":[159],"text-to-speech":[160],"applications.":[161]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}