{"id":"https://openalex.org/W2801291345","doi":"https://doi.org/10.1109/icassp.2018.8462237","title":"An Investigation of Subband Wavenet Vocoder Covering Entire Audible Frequency Range with Limited Acoustic Features","display_name":"An Investigation of Subband Wavenet Vocoder Covering Entire Audible Frequency Range with Limited Acoustic Features","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2801291345","doi":"https://doi.org/10.1109/icassp.2018.8462237","mag":"2801291345"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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"],"raw_orcid":null,"affiliations":[{"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/A5100925892","display_name":"Kentaro Tachibana","orcid":null},"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":"Kentaro Tachibana","raw_affiliation_strings":["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"]}]},{"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Information Technology Center, Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109350986","display_name":"Yoshinori Shiga","orcid":null},"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":"Yoshinori Shiga","raw_affiliation_strings":["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"]}]},{"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"],"raw_orcid":null,"affiliations":[{"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":30,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5654","last_page":"5658"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.9959999918937683,"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":0.742023229598999},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.621408998966217},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.556455135345459},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4990530014038086},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.49407628178596497},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4758733808994293},{"id":"https://openalex.org/keywords/fundamental-frequency","display_name":"Fundamental frequency","score":0.4273705780506134},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4242384433746338},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1360844075679779},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.11784398555755615},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07454073429107666}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.742023229598999},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.621408998966217},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.556455135345459},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4990530014038086},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.49407628178596497},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4758733808994293},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.4273705780506134},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4242384433746338},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1360844075679779},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.11784398555755615},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07454073429107666},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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":39,"referenced_works":["https://openalex.org/W198589515","https://openalex.org/W2043003570","https://openalex.org/W2049686551","https://openalex.org/W2093450784","https://openalex.org/W2111284386","https://openalex.org/W2395849284","https://openalex.org/W2403471241","https://openalex.org/W2417163358","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2576309025","https://openalex.org/W2584032004","https://openalex.org/W2591927543","https://openalex.org/W2592040118","https://openalex.org/W2598638573","https://openalex.org/W2619368999","https://openalex.org/W2746474733","https://openalex.org/W2749651610","https://openalex.org/W2766812927","https://openalex.org/W2785516183","https://openalex.org/W2786868129","https://openalex.org/W2789740382","https://openalex.org/W2797310469","https://openalex.org/W2901997113","https://openalex.org/W2964115871","https://openalex.org/W2964243274","https://openalex.org/W4294619240","https://openalex.org/W6607999264","https://openalex.org/W6713400016","https://openalex.org/W6732429163","https://openalex.org/W6734596677","https://openalex.org/W6734815144","https://openalex.org/W6736734616","https://openalex.org/W6738277540","https://openalex.org/W6742995815","https://openalex.org/W6745697700","https://openalex.org/W6746700228","https://openalex.org/W6751256898","https://openalex.org/W6756197946"],"related_works":["https://openalex.org/W2216757598","https://openalex.org/W234770729","https://openalex.org/W4387496629","https://openalex.org/W2050184091","https://openalex.org/W3013209356","https://openalex.org/W2489800615","https://openalex.org/W2070597833","https://openalex.org/W2064065729","https://openalex.org/W2616987818","https://openalex.org/W1998765649"],"abstract_inverted_index":{"Although":[0],"a":[1,54,58,62,69,75,80,86,97,107,116],"WaveNet":[2,59,77,82,88,95,126],"vocoder":[3,60,83,127],"can":[4],"synthesize":[5],"more":[6],"natural-sounding":[7],"speech":[8,119],"waveforms":[9],"than":[10],"conventional":[11,136],"vocoders":[12,139],"with":[13,53,61,68,96,115,128,142],"sampling":[14,28,63,98],"frequencies":[15],"of":[16,65,100,112],"16":[17],"and":[18,84],"24":[19],"kHz,":[20],"it":[21],"is":[22],"difficult":[23],"to":[24,30,33,51,79],"directly":[25],"extend":[26],"the":[27,35,45,123,135],"frequency":[29,39,64,99],"48":[31,66],"kHz":[32,67,102],"cover":[34],"entire":[36],"human":[37],"audible":[38],"range":[40],"for":[41],"higher-quality":[42],"synthesis":[43],"because":[44],"model":[46],"size":[47],"becomes":[48],"too":[49],"large":[50],"train":[52],"consumer":[55,70,108],"GPU.":[56,109],"For":[57],"GPU,":[71],"this":[72],"paper":[73],"introduces":[74],"subband":[76,87,94,125],"architecture":[78],"speaker-dependent":[81],"proposes":[85],"vocoder.":[89],"In":[90],"experiments,":[91],"each":[92],"conditional":[93],"8":[101],"was":[103],"well":[104],"trained":[105],"using":[106],"The":[110],"results":[111],"subjective":[113],"evaluations":[114],"Japanese":[117],"male":[118],"corpus":[120],"indicate":[121],"that":[122],"proposed":[124],"36-dimensional":[129],"simple":[130],"acoustic":[131],"features":[132],"significantly":[133],"outperformed":[134],"source-filter":[137],"model-based":[138],"including":[140],"STRAIGHT":[141],"86-dimensional":[143],"features.":[144]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}