{"id":"https://openalex.org/W2898847420","doi":"https://doi.org/10.1109/icassp.2019.8683143","title":"Waveglow: A Flow-based Generative Network for Speech Synthesis","display_name":"Waveglow: A Flow-based Generative Network for Speech Synthesis","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2898847420","doi":"https://doi.org/10.1109/icassp.2019.8683143","mag":"2898847420"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683143","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683143","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1811.00002","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010578786","display_name":"Ryan Prenger","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ryan Prenger","raw_affiliation_strings":["NVIDIA Corporation","NVIDIA Corporation#TAB#"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA Corporation#TAB#","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113576287","display_name":"Rafael Valle","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rafael Valle","raw_affiliation_strings":["NVIDIA Corporation","NVIDIA Corporation#TAB#"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA Corporation#TAB#","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066242985","display_name":"Bryan Catanzaro","orcid":"https://orcid.org/0000-0003-0034-7728"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bryan Catanzaro","raw_affiliation_strings":["NVIDIA Corporation","NVIDIA Corporation#TAB#"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA Corporation#TAB#","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5010578786"],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":9.19408511,"has_fulltext":true,"cited_by_count":75,"citation_normalized_percentile":{"value":0.98565033,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3617","last_page":"3621"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9994000196456909,"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":0.8420089483261108},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7201799750328064},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5588847398757935},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5330207347869873},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5122167468070984},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.5049014687538147},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.46121442317962646},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.44278404116630554},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32821542024612427},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.271017462015152},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10279136896133423}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8420089483261108},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7201799750328064},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5588847398757935},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5330207347869873},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5122167468070984},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.5049014687538147},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.46121442317962646},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.44278404116630554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32821542024612427},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.271017462015152},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10279136896133423},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2019.8683143","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683143","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1811.00002","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.00002","pdf_url":"https://arxiv.org/pdf/1811.00002","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2898847420","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1811.00002","pdf_url":null,"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":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.1811.00002","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1811.00002","pdf_url":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1811.00002","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.00002","pdf_url":"https://arxiv.org/pdf/1811.00002","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5400000214576721,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2898847420.pdf","grobid_xml":"https://content.openalex.org/works/W2898847420.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W299440670","https://openalex.org/W1522301498","https://openalex.org/W1583912456","https://openalex.org/W2120847449","https://openalex.org/W2284050935","https://openalex.org/W2409550820","https://openalex.org/W2591927543","https://openalex.org/W2608207374","https://openalex.org/W2619368999","https://openalex.org/W2769810959","https://openalex.org/W2777302760","https://openalex.org/W2788851830","https://openalex.org/W2883853252","https://openalex.org/W2888169323","https://openalex.org/W2890983311","https://openalex.org/W2949382160","https://openalex.org/W6610566761","https://openalex.org/W6631190155","https://openalex.org/W6635084905","https://openalex.org/W6695676441","https://openalex.org/W6714644935","https://openalex.org/W6733471323","https://openalex.org/W6734815144","https://openalex.org/W6736356763","https://openalex.org/W6738277540","https://openalex.org/W6746700228","https://openalex.org/W6748409065","https://openalex.org/W6752910514","https://openalex.org/W6753855596","https://openalex.org/W6754091617","https://openalex.org/W6763509872"],"related_works":["https://openalex.org/W2949382160","https://openalex.org/W2899882692","https://openalex.org/W2964121744","https://openalex.org/W2963975282","https://openalex.org/W2471520273","https://openalex.org/W1959608418","https://openalex.org/W2970006822","https://openalex.org/W2963609956","https://openalex.org/W2963139417","https://openalex.org/W2890983311","https://openalex.org/W2788851830","https://openalex.org/W2769810959","https://openalex.org/W2749651610","https://openalex.org/W2409550820","https://openalex.org/W2963047245","https://openalex.org/W2099471712","https://openalex.org/W1583912456","https://openalex.org/W3048173247","https://openalex.org/W3154231781","https://openalex.org/W3015338123"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"propose":[4],"WaveGlow:":[5],"a":[6,44,50,76],"flow-based":[7],"network":[8],"capable":[9],"of":[10,57,78],"generating":[11],"high":[12],"quality":[13,96],"speech":[14],"from":[15,20],"mel-spectrograms.":[16],"WaveGlow":[17,39],"combines":[18],"insights":[19],"Glow":[21],"and":[22,30,67],"WaveNet":[23,104],"in":[24],"order":[25],"to":[26],"provide":[27],"fast,":[28],"efficient":[29],"high-quality":[31],"audio":[32,73,95],"synthesis,":[33],"without":[34],"the":[35,55,58,63,100],"need":[36],"for":[37],"auto-regression.":[38],"is":[40],"implemented":[41],"using":[42,48],"only":[43,49],"single":[45,51],"network,":[46],"trained":[47],"cost":[52],"function:":[53],"maximizing":[54],"likelihood":[56],"training":[59,64],"data,":[60],"which":[61],"makes":[62],"procedure":[65],"simple":[66],"stable.":[68],"Our":[69],"PyTorch":[70],"implementation":[71],"produces":[72],"samples":[74],"at":[75],"rate":[77],"more":[79],"than":[80],"500":[81],"kHz":[82],"on":[83],"an":[84],"NVIDIA":[85],"V100":[86],"GPU.":[87],"Mean":[88],"Opinion":[89],"Scores":[90],"show":[91],"that":[92],"it":[93],"delivers":[94],"as":[97,99],"good":[98],"best":[101],"publicly":[102,111],"available":[103,112],"implementation.":[105],"All":[106],"code":[107],"will":[108],"be":[109],"made":[110],"online.":[113]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":21},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}