{"id":"https://openalex.org/W3162075194","doi":"https://doi.org/10.1109/icassp39728.2021.9415087","title":"Noise Level Limited Sub-Modeling for Diffusion Probabilistic Vocoders","display_name":"Noise Level Limited Sub-Modeling for Diffusion Probabilistic Vocoders","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162075194","doi":"https://doi.org/10.1109/icassp39728.2021.9415087","mag":"3162075194"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9415087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9415087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/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","Information Technology Center, Nagoya University, Japan","National Institute of Information and Communications Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Information Technology Center,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Information Technology Center, 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":"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","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":"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":"6029","last_page":"6033"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987000226974487,"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":0.9945999979972839,"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":0.7443325519561768},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.7241899967193604},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6291199922561646},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5223106741905212},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47315582633018494},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.45228123664855957},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.45182815194129944},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4399336874485016},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3149430751800537},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.22591304779052734},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06472885608673096}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7443325519561768},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.7241899967193604},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6291199922561646},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5223106741905212},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47315582633018494},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.45228123664855957},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.45182815194129944},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4399336874485016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3149430751800537},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.22591304779052734},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06472885608673096},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9415087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9415087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","score":0.6200000047683716,"display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W2013035813","https://openalex.org/W2099471712","https://openalex.org/W2169711598","https://openalex.org/W2519091744","https://openalex.org/W2749651610","https://openalex.org/W2769810959","https://openalex.org/W2959300817","https://openalex.org/W2962882868","https://openalex.org/W2963090522","https://openalex.org/W2963091184","https://openalex.org/W2963300588","https://openalex.org/W2963782041","https://openalex.org/W2963975282","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W2968917279","https://openalex.org/W2970006822","https://openalex.org/W2971034910","https://openalex.org/W2975414524","https://openalex.org/W2990440871","https://openalex.org/W2993118648","https://openalex.org/W2994689640","https://openalex.org/W2996286887","https://openalex.org/W3007859642","https://openalex.org/W3015338123","https://openalex.org/W3016136182","https://openalex.org/W3024102405","https://openalex.org/W3025942077","https://openalex.org/W3035068567","https://openalex.org/W3035083561","https://openalex.org/W3036167779","https://openalex.org/W3038172701","https://openalex.org/W3092028330","https://openalex.org/W3096702751","https://openalex.org/W3097828251","https://openalex.org/W3097895838","https://openalex.org/W3098403858","https://openalex.org/W3100572490","https://openalex.org/W3123097577","https://openalex.org/W3125708547","https://openalex.org/W3129651364","https://openalex.org/W3144035034","https://openalex.org/W4287761884","https://openalex.org/W4289305009","https://openalex.org/W4294619240","https://openalex.org/W4298580827","https://openalex.org/W4320013936","https://openalex.org/W6610566761","https://openalex.org/W6748409065","https://openalex.org/W6753855596","https://openalex.org/W6756159577","https://openalex.org/W6765775151","https://openalex.org/W6767111847","https://openalex.org/W6767164110","https://openalex.org/W6771024825","https://openalex.org/W6776594914","https://openalex.org/W6779337556","https://openalex.org/W6779823529","https://openalex.org/W6779871621","https://openalex.org/W6782760101","https://openalex.org/W6783182287","https://openalex.org/W6783867762"],"related_works":["https://openalex.org/W2171117985","https://openalex.org/W1526760723","https://openalex.org/W2126659863","https://openalex.org/W2012356576","https://openalex.org/W4385670989","https://openalex.org/W3112120395","https://openalex.org/W2102487628","https://openalex.org/W2436588531","https://openalex.org/W2009680848","https://openalex.org/W2150465873"],"abstract_inverted_index":{"Although":[0],"diffusion":[1,51],"probabilistic":[2,52],"vocoders":[3,53],"WaveGrad":[4,131],"and":[5,55,70,80,98,127,132,140],"DiffWave":[6,61,133],"can":[7],"realize":[8],"real-time":[9],"high-fidelity":[10],"speech":[11,119],"synthesis":[12,141],"with":[13,23,93],"a":[14,42,64,116],"simple":[15,43],"loss":[16],"function":[17],"in":[18,36,134],"training,":[19],"all":[20,37],"noise":[21,29,46,66,95,107],"components":[22],"over":[24],"the":[25,58,106,124,137,145],"full":[26],"range":[27],"of":[28,113,136],"levels":[30],"are":[31,74,83,90,102],"predicted":[32],"by":[33],"one":[34],"model":[35,138],"iterations.":[38],"This":[39],"paper":[40],"proposes":[41],"but":[44],"effective":[45],"level-limited":[47],"sub-modeling":[48],"framework":[49],"for":[50],"Sub-WaveGrad":[54,79,126],"Sub-DiffWave.":[56],"In":[57],"proposed":[59,78,125],"method,":[60],"conditioned":[62],"on":[63],"continuous":[65],"level":[67,96],"like":[68],"WaveGrad,":[69],"spectral":[71],"enhancement":[72],"post-filtering":[73],"also":[75],"provided.":[76],"The":[77,111],"Sub-DiffWave":[81,128],"models":[82,89],"realized":[84],"using":[85,115],"10":[86],"sub-models.":[87],"These":[88],"separately":[91],"trained":[92],"different":[94],"limits,":[97],"only":[99],"necessary":[100],"sub-models":[101],"used":[103],"according":[104],"to":[105],"schedule":[108],"during":[109],"inference.":[110],"results":[112],"experiments":[114],"Japanese":[117],"female":[118],"corpus":[120],"indicate":[121],"that":[122],"both":[123],"outperform":[129],"vanilla":[130],"terms":[135],"accuracy":[139],"quality":[142],"while":[143],"retaining":[144],"inference":[146],"speed.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
