{"id":"https://openalex.org/W4392903256","doi":"https://doi.org/10.1109/icassp48485.2024.10446890","title":"Convnext-TTS And Convnext-VC: Convnext-Based Fast End-To-End Sequence-To-Sequence Text-To-Speech And Voice Conversion","display_name":"Convnext-TTS And Convnext-VC: Convnext-Based Fast End-To-End Sequence-To-Sequence Text-To-Speech And Voice Conversion","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903256","doi":"https://doi.org/10.1109/icassp48485.2024.10446890"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446890","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446890","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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,Information Technology Center,Japan","National Institute of Information and Communications Technology, Japan","Information Technology Center, Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Information Technology Center,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"Information Technology Center, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"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":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12456","last_page":"12460"},"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":0.9882000088691711,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9842000007629395,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7466899156570435},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7402253150939941},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6332242488861084},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6113495826721191},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5652942657470703},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5259361863136292},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.49333062767982483},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4411267638206482},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4233006238937378},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31542742252349854},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11365261673927307},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.05365687608718872},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.050768643617630005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7466899156570435},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7402253150939941},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6332242488861084},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6113495826721191},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5652942657470703},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5259361863136292},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.49333062767982483},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4411267638206482},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4233006238937378},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31542742252349854},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11365261673927307},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.05365687608718872},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.050768643617630005},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446890","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446890","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2331143823","https://openalex.org/W2473388484","https://openalex.org/W2531409750","https://openalex.org/W2747070883","https://openalex.org/W2795374598","https://openalex.org/W2903739847","https://openalex.org/W3015719750","https://openalex.org/W3128170746","https://openalex.org/W3138516171","https://openalex.org/W3162517041","https://openalex.org/W3168719651","https://openalex.org/W3196001064","https://openalex.org/W3206375275","https://openalex.org/W4210287297","https://openalex.org/W4221152438","https://openalex.org/W4312443924","https://openalex.org/W4379259581","https://openalex.org/W4385245566","https://openalex.org/W4385822333","https://openalex.org/W4385822605","https://openalex.org/W4385823163","https://openalex.org/W4385823165","https://openalex.org/W4385993937","https://openalex.org/W4391021821","https://openalex.org/W6763832098","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6796464841","https://openalex.org/W6802659129","https://openalex.org/W6810302181","https://openalex.org/W6853165267"],"related_works":["https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W1999612375","https://openalex.org/W2938107654","https://openalex.org/W4390516098","https://openalex.org/W3008587939","https://openalex.org/W4206178588","https://openalex.org/W3094491777","https://openalex.org/W3214715529","https://openalex.org/W4287635093"],"abstract_inverted_index":{"End-to-end":[0],"(E2E)":[1],"sequence-to-sequence":[2],"(S2S)":[3],"neural":[4,10,23,66],"text-to-speech":[5],"(TTS)":[6],"models":[7,14,36],"and":[8,34,37,48,60,75,94,103,115,125,132],"E2E-S2S":[9,32],"voice":[11],"conversion":[12],"(VC)":[13],"can":[15,76,105,127],"achieve":[16,77,128],"high-quality":[17],"speech":[18],"synthesis":[19,29,80,120],"with":[20,134],"a":[21,44,112,135,141],"single":[22],"network.":[24],"To":[25],"further":[26,52],"improve":[27],"the":[28,54,64,88,92,99,119],"quality":[30],"of":[31,85,138],"TTS":[33],"VC":[35],"increase":[38,53],"their":[39],"inference":[40,55,107],"speed,":[41,56],"we":[42,57],"propose":[43,58],"Transformer-free":[45],"ConvNeXt-based":[46,101],"encoder":[47,102,114],"decoder.":[49],"Additionally,":[50],"to":[51],"ConvNeXt-TTS":[59,124],"ConvNeXt-VC,":[61],"which":[62],"include":[63],"WaveNeXt":[65],"vocoder.":[67],"This":[68],"is":[69],"also":[70],"constructed":[71],"from":[72],"ConvNeXt":[73],"blocks":[74],"much":[78],"faster":[79,110],"than":[81,111],"HiFi-GAN.":[82],"The":[83],"results":[84],"experiments":[86],"using":[87,140],"Hi-Fi-CAPTAIN":[89],"corpus":[90],"for":[91],"E2E-S2S-TTS":[93,131],"E2E-S2S-VC":[95,133],"conditions":[96],"demonstrate":[97],"that":[98],"proposed":[100],"decoder":[104,116],"perform":[106],"three":[108],"times":[109],"Transformer-based":[113],"while":[117],"improving":[118],"quality.":[121],"In":[122],"particular,":[123],"ConvNeXt-VC":[126],"very":[129],"fast":[130],"real-time":[136],"factor":[137],"0.05":[139],"single-core":[142],"CPU.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
