{"id":"https://openalex.org/W4391021821","doi":"https://doi.org/10.1109/asru57964.2023.10389765","title":"WaveNeXt: ConvNeXt-Based Fast Neural Vocoder Without ISTFT layer","display_name":"WaveNeXt: ConvNeXt-Based Fast Neural Vocoder Without ISTFT layer","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021821","doi":"https://doi.org/10.1109/asru57964.2023.10389765"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389765","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389765","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5022943637","display_name":"Takuma Okamoto","orcid":"https://orcid.org/0000-0001-9913-4647"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuma Okamoto","raw_affiliation_strings":["National Institute of Information and Communications Technology,Japan","National Institute of Information and Communications Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology,Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085108313","display_name":"Haruki Yamashita","orcid":"https://orcid.org/0009-0001-8553-9317"},"institutions":[{"id":"https://openalex.org/I65837984","display_name":"Kobe University","ror":"https://ror.org/03tgsfw79","country_code":"JP","type":"education","lineage":["https://openalex.org/I65837984"]},{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Haruki Yamashita","raw_affiliation_strings":["Kobe University,Japan","National Institute of Information and Communications Technology, Japan","Kobe University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kobe University,Japan","institution_ids":["https://openalex.org/I65837984"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"Kobe University, Japan","institution_ids":["https://openalex.org/I65837984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018533235","display_name":"Yamato Ohtani","orcid":"https://orcid.org/0009-0009-2961-2821"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yamato Ohtani","raw_affiliation_strings":["National Institute of Information and Communications Technology,Japan","National Institute of Information and Communications Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology,Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]},{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan","National Institute of Information and Communications Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114514387","display_name":"Hisashi Kawai","orcid":"https://orcid.org/0000-0002-0914-5092"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hisashi Kawai","raw_affiliation_strings":["National Institute of Information and Communications Technology,Japan","National Institute of Information and Communications Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology,Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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":0.9961000084877014,"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/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.8523667454719543},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7488926649093628},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6553093194961548},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5268900394439697},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5188937783241272},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.5156842470169067},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49860143661499023},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.4814719259738922},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46114689111709595},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4544622302055359},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.41632428765296936},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3700735569000244},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35568225383758545},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.15492549538612366},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14041703939437866},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.09417745471000671},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07620391249656677}],"concepts":[{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.8523667454719543},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7488926649093628},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6553093194961548},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5268900394439697},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5188937783241272},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.5156842470169067},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49860143661499023},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.4814719259738922},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46114689111709595},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4544622302055359},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.41632428765296936},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3700735569000244},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35568225383758545},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.15492549538612366},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14041703939437866},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.09417745471000671},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07620391249656677},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389765","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389765","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W2093112233","https://openalex.org/W2172065531","https://openalex.org/W2471520273","https://openalex.org/W2476548250","https://openalex.org/W2531409750","https://openalex.org/W2747070883","https://openalex.org/W2747874407","https://openalex.org/W2785516183","https://openalex.org/W2795374598","https://openalex.org/W2801291345","https://openalex.org/W2899663614","https://openalex.org/W2912237252","https://openalex.org/W2963091184","https://openalex.org/W2998572311","https://openalex.org/W3128170746","https://openalex.org/W3138516171","https://openalex.org/W3144035034","https://openalex.org/W3162075194","https://openalex.org/W3163793923","https://openalex.org/W3165891254","https://openalex.org/W3168719651","https://openalex.org/W3196001064","https://openalex.org/W3196468212","https://openalex.org/W3197273793","https://openalex.org/W3198843334","https://openalex.org/W3206375275","https://openalex.org/W3215615641","https://openalex.org/W4210287297","https://openalex.org/W4221152438","https://openalex.org/W4224612669","https://openalex.org/W4226421894","https://openalex.org/W4312443924","https://openalex.org/W4319862245","https://openalex.org/W4320730519","https://openalex.org/W4372190416","https://openalex.org/W4372262501","https://openalex.org/W4372266901","https://openalex.org/W4372270198","https://openalex.org/W4372270423","https://openalex.org/W4372341094","https://openalex.org/W4372341178","https://openalex.org/W4372347654","https://openalex.org/W4372348373","https://openalex.org/W4379259581","https://openalex.org/W4382296240","https://openalex.org/W4385822605","https://openalex.org/W4385823165","https://openalex.org/W4386076493","https://openalex.org/W6748409065","https://openalex.org/W6755977528","https://openalex.org/W6766978945","https://openalex.org/W6767111847","https://openalex.org/W6772349387","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6779469704","https://openalex.org/W6780226713","https://openalex.org/W6782760101","https://openalex.org/W6783182287","https://openalex.org/W6783867762","https://openalex.org/W6796464841","https://openalex.org/W6802659129","https://openalex.org/W6802838302","https://openalex.org/W6805710207","https://openalex.org/W6853165267"],"related_works":["https://openalex.org/W1974895211","https://openalex.org/W2176409448","https://openalex.org/W2129841057","https://openalex.org/W3040712279","https://openalex.org/W2364769705","https://openalex.org/W4225639054","https://openalex.org/W4200633555","https://openalex.org/W2039489009","https://openalex.org/W2143985734","https://openalex.org/W1967434260"],"abstract_inverted_index":{"A":[0],"recently":[1],"proposed":[2,126],"neural":[3,50],"vocoder,":[4,51],"Vocos,":[5],"can":[6,22,69,91,128],"perform":[7],"inference":[8,41,138],"ten":[9],"times":[10],"faster":[11],"than":[12,133],"HiFi-GAN":[13],"because":[14],"of":[15,18,106,113],"its":[16,137],"use":[17],"ConvNeXt":[19],"layers":[20],"that":[21,68,124],"predict":[23,71],"high-resolution":[24],"short-time":[25],"Fourier":[26],"transform":[27],"(STFT)":[28],"spectra":[29],"and":[30,97,119],"an":[31,46],"inverse":[32,56],"STFT":[33,57,76],"layer.":[34],"To":[35],"improve":[36],"synthesis":[37,132],"quality":[38,131],"while":[39,135],"preserving":[40,136],"speed,":[42],"this":[43],"paper":[44],"proposes":[45],"alternative":[47],"ConvNeXt-based":[48],"fast":[49],"WaveNeXt,":[52],"in":[53,59],"which":[54],"the":[55,81,117,125],"layer":[58,67],"Vocos":[60,96,134],"is":[61],"replaced":[62],"with":[63,95,102],"a":[64,103],"trainable":[65],"linear":[66],"directly":[70],"speech":[72],"waveform":[73],"samples":[74],"without":[75],"spectra.":[77],"Additionally,":[78],"by":[79],"integrating":[80],"JETS-based":[82],"end-to-end":[83],"text-to-speech":[84],"(E2E":[85],"TTS)":[86],"framework,":[87],"E2E":[88,120],"TTS":[89,121],"models":[90,101],"also":[92],"be":[93],"constructed":[94],"WaveNeXt.":[98],"Furthermore,":[99],"full-band":[100],"sampling":[104],"frequency":[105],"48":[107],"kHz":[108],"were":[109],"investigated.":[110],"The":[111],"results":[112],"experiments":[114],"for":[115],"both":[116],"analysis-synthesis":[118],"conditions":[122],"demonstrate":[123],"WaveNeXt":[127],"achieve":[129],"higher":[130],"speed.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}