{"id":"https://openalex.org/W4221152438","doi":"https://doi.org/10.1109/icassp43922.2022.9746713","title":"ISTFTNET: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform","display_name":"ISTFTNET: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221152438","doi":"https://doi.org/10.1109/icassp43922.2022.9746713"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746713","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746713","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5020693766","display_name":"Takuhiro Kaneko","orcid":"https://orcid.org/0009-0000-8016-5144"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takuhiro Kaneko","raw_affiliation_strings":["NTT Corporation,NTT Communication Science Laboratories,Japan","NTT Communication Science Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Communication Science Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004248530","display_name":"Kou Tanaka","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kou Tanaka","raw_affiliation_strings":["NTT Corporation,NTT Communication Science Laboratories,Japan","NTT Communication Science Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Communication Science Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001243214","display_name":"Hirokazu Kameoka","orcid":"https://orcid.org/0000-0003-3102-0162"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirokazu Kameoka","raw_affiliation_strings":["NTT Corporation,NTT Communication Science Laboratories,Japan","NTT Communication Science Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Communication Science Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018003761","display_name":"Shogo Seki","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shogo Seki","raw_affiliation_strings":["NTT Corporation,NTT Communication Science Laboratories,Japan","NTT Communication Science Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,NTT Communication Science Laboratories,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5020693766"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":6.0289,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":{"value":0.97175411,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6207","last_page":"6211"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9980999827384949,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/spectrogram","display_name":"Spectrogram","score":0.9714913964271545},{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.732174813747406},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6878563165664673},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6354135274887085},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6077499985694885},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4882371723651886},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.45549237728118896},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.4401724338531494},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.4388164281845093},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.42964133620262146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3055647611618042},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18903475999832153},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.16845926642417908},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1148882806301117}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9714913964271545},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.732174813747406},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6878563165664673},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6354135274887085},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6077499985694885},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4882371723651886},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.45549237728118896},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.4401724338531494},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.4388164281845093},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.42964133620262146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3055647611618042},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18903475999832153},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.16845926642417908},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1148882806301117},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746713","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746713","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2194775991","https://openalex.org/W2202109488","https://openalex.org/W2519091744","https://openalex.org/W2593414223","https://openalex.org/W2769810959","https://openalex.org/W2903739847","https://openalex.org/W2945478979","https://openalex.org/W2946200149","https://openalex.org/W2959300817","https://openalex.org/W2963300588","https://openalex.org/W2963691546","https://openalex.org/W2963975282","https://openalex.org/W2964167449","https://openalex.org/W2964243274","https://openalex.org/W2964328256","https://openalex.org/W2970006822","https://openalex.org/W2971753973","https://openalex.org/W2973203693","https://openalex.org/W2975414524","https://openalex.org/W2996286887","https://openalex.org/W3015338123","https://openalex.org/W3016160783","https://openalex.org/W3033411150","https://openalex.org/W3036167779","https://openalex.org/W3036601975","https://openalex.org/W3092028330","https://openalex.org/W3095936335","https://openalex.org/W3097777922","https://openalex.org/W3097828251","https://openalex.org/W3123097577","https://openalex.org/W3129651364","https://openalex.org/W3144035034","https://openalex.org/W3161236344","https://openalex.org/W3162512456","https://openalex.org/W3163793923","https://openalex.org/W4287694050","https://openalex.org/W4294619240","https://openalex.org/W4298580827","https://openalex.org/W4301206121","https://openalex.org/W4320013936","https://openalex.org/W6631190155","https://openalex.org/W6748409065","https://openalex.org/W6749489859","https://openalex.org/W6753855596","https://openalex.org/W6762533536","https://openalex.org/W6763832098","https://openalex.org/W6765775151","https://openalex.org/W6765779288","https://openalex.org/W6767111847","https://openalex.org/W6767453231","https://openalex.org/W6778823374","https://openalex.org/W6779823529","https://openalex.org/W6780218876","https://openalex.org/W6781251213","https://openalex.org/W6782760101","https://openalex.org/W6783182287","https://openalex.org/W6783867762","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2120540196","https://openalex.org/W3095343173","https://openalex.org/W2381036744","https://openalex.org/W2288135719","https://openalex.org/W2323749021","https://openalex.org/W2533590149","https://openalex.org/W2901989338","https://openalex.org/W82005754","https://openalex.org/W2334448276","https://openalex.org/W3210733254"],"abstract_inverted_index":{"In":[0],"recent":[1],"text-to-speech":[2],"synthesis":[3,80],"and":[4,17,42,54,100,147,165,170],"voice":[5],"conversion":[6],"systems,":[7],"a":[8,21,57,68,97,109,174],"mel-spectrogram":[9,22,27,48,122],"is":[10,24],"commonly":[11],"applied":[12,158],"as":[13],"an":[14,72],"intermediate":[15],"representation,":[16],"the":[18,36,82,91,104,121,125,134,141,167],"necessity":[19],"for":[20],"vocoder":[23,28,49,123],"increasing.":[25],"A":[26,45],"must":[29],"solve":[30],"three":[31,162],"inverse":[32,126],"problems:":[33],"recovery":[34],"of":[35,85,120,151],"original-scale":[37,87],"magnitude":[38],"spectrogram,":[39],"phase":[40],"reconstruction,":[41],"frequency-to-time":[43],"conversion.":[44],"typical":[46],"convolutional":[47,58],"solves":[50,93],"these":[51],"problems":[52,95],"jointly":[53],"implicitly":[55],"using":[56,137],"neural":[59],"network,":[60],"including":[61],"temporal":[62],"upsampling":[63,138],"layers,":[64,139],"when":[65],"directly":[66],"calculating":[67],"raw":[69],"waveform.":[70],"Such":[71],"approach":[73,92],"allows":[74],"skipping":[75],"redundant":[76,149],"processes":[77],"during":[78],"waveform":[79],"(e.g.,":[81],"direct":[83],"reconstruction":[84],"high-dimensional":[86,152],"spectrograms).":[88],"By":[89],"contrast,":[90],"all":[94],"in":[96,108],"black":[98],"box":[99],"cannot":[101],"effectively":[102],"employ":[103],"time-frequency":[105],"structures":[106],"existing":[107],"mel-spectrogram.":[110],"We":[111],"thus":[112],"propose":[113],"iSTFTNet,":[114],"which":[115],"replaces":[116],"some":[117],"output-side":[118],"layers":[119],"with":[124,173],"short-time":[127],"Fourier":[128],"transform":[129],"(iSTFT)":[130],"after":[131],"sufficiently":[132],"reducing":[133,140],"frequency":[135],"dimension":[136],"computational":[142],"cost":[143],"from":[144],"black-box":[145],"modeling":[146],"avoiding":[148],"estimations":[150],"spectrograms.":[153],"During":[154],"our":[155,159],"experiments,":[156],"we":[157],"ideas":[160],"to":[161],"HiFi-GAN":[163],"variants":[164],"made":[166],"models":[168],"faster":[169],"more":[171],"lightweight":[172],"reasonable":[175],"speech":[176],"quality.":[177],"<sup":[178],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[179],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[180]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":2}],"updated_date":"2026-05-08T15:41:06.802602","created_date":"2025-10-10T00:00:00"}