{"id":"https://openalex.org/W4225566824","doi":"https://doi.org/10.21437/interspeech.2022-301","title":"SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shaping","display_name":"SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shaping","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4225566824","doi":"https://doi.org/10.21437/interspeech.2022-301"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-301","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-301","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5101503856","display_name":"Yuma Koizumi","orcid":"https://orcid.org/0000-0003-3645-6213"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yuma Koizumi","raw_affiliation_strings":["Google Research,"],"affiliations":[{"raw_affiliation_string":"Google Research,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003420204","display_name":"Heiga Zen","orcid":"https://orcid.org/0000-0002-8959-5471"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heiga Zen","raw_affiliation_strings":["Google Research,"],"affiliations":[{"raw_affiliation_string":"Google Research,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034837951","display_name":"Kohei Yatabe","orcid":"https://orcid.org/0000-0002-1345-0663"},"institutions":[{"id":"https://openalex.org/I92614990","display_name":"Tokyo University of Agriculture and Technology","ror":"https://ror.org/00qg0kr10","country_code":"JP","type":"education","lineage":["https://openalex.org/I92614990"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kohei Yatabe","raw_affiliation_strings":["Tokyo University of Agriculture and Technology"],"affiliations":[{"raw_affiliation_string":"Tokyo University of Agriculture and Technology","institution_ids":["https://openalex.org/I92614990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049929716","display_name":"Nanxin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nanxin Chen","raw_affiliation_strings":["Google Research,"],"affiliations":[{"raw_affiliation_string":"Google Research,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059692696","display_name":"Michiel Bacchiani","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michiel Bacchiani","raw_affiliation_strings":["Google Research,"],"affiliations":[{"raw_affiliation_string":"Google Research,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101503856"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":3.9326,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.95481833,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976999759674072,"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":0.9900000095367432,"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":0.7092105150222778},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7044528722763062},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5922847986221313},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.582483172416687},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.529424250125885},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.34040704369544983},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3016052842140198},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11069023609161377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7092105150222778},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7044528722763062},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5922847986221313},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.582483172416687},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.529424250125885},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.34040704369544983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3016052842140198},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11069023609161377},{"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-301","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-301","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1527535554","https://openalex.org/W2117678320","https://openalex.org/W2144404214","https://openalex.org/W2338186431","https://openalex.org/W2516001803","https://openalex.org/W2519091744","https://openalex.org/W2749651610","https://openalex.org/W2929299742","https://openalex.org/W2963300588","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W2990440871","https://openalex.org/W2993118648","https://openalex.org/W2998498479","https://openalex.org/W3015338123","https://openalex.org/W3015626488","https://openalex.org/W3036167779","https://openalex.org/W3092028330","https://openalex.org/W3096159803","https://openalex.org/W3123097577","https://openalex.org/W3129651364","https://openalex.org/W3160077247","https://openalex.org/W3161541317","https://openalex.org/W3162075194","https://openalex.org/W3172148458","https://openalex.org/W3203491020","https://openalex.org/W3204728450","https://openalex.org/W4200483526","https://openalex.org/W4221152471","https://openalex.org/W4224931676","https://openalex.org/W4226213470","https://openalex.org/W4287120591","https://openalex.org/W4287694050","https://openalex.org/W4297817572","https://openalex.org/W4298580827","https://openalex.org/W4300943593"],"related_works":["https://openalex.org/W2494523064","https://openalex.org/W2943623134","https://openalex.org/W2215759665","https://openalex.org/W2960358116","https://openalex.org/W2030292806","https://openalex.org/W2147155098","https://openalex.org/W4287727129","https://openalex.org/W3041172967","https://openalex.org/W2588219639","https://openalex.org/W2938171715"],"abstract_inverted_index":{"Neural":[0],"vocoder":[1],"using":[2],"denoising":[3],"diffusion":[4,15,30],"probabilistic":[5],"model":[6],"(DDPM)":[7],"has":[8],"been":[9],"improved":[10],"by":[11,46],"adaptation":[12,45],"of":[13],"the":[14,29,41,50,55,61,66,70,73],"noise":[16,31],"distribution":[17],"to":[18,40,64],"given":[19],"acoustic":[20],"features.In":[21],"this":[22],"study,":[23],"we":[24],"propose":[25],"SpecGrad":[26],"that":[27,33,80],"adapts":[28],"so":[32],"its":[34],"timevarying":[35],"spectral":[36],"envelope":[37],"becomes":[38],"close":[39],"conditioning":[42],"log-mel":[43],"spectrogram.This":[44],"time-varying":[47],"filtering":[48],"improves":[49],"sound":[51],"quality":[52],"especially":[53],"in":[54,60,91],"high-frequency":[56],"bands.It":[57],"is":[58],"processed":[59],"time-frequency":[62],"domain":[63],"keep":[65],"computational":[67],"cost":[68],"almost":[69],"same":[71],"as":[72],"conventional":[74,87],"DDPMbased":[75],"neural":[76,89],"vocoders.Experimental":[77],"results":[78],"showed":[79],"Spec-Grad":[81],"generates":[82],"higher-fidelity":[83],"speech":[84,95],"waveform":[85],"than":[86],"DDPM-based":[88],"vocoders":[90],"both":[92],"analysis-synthesis":[93],"and":[94],"enhancement":[96],"scenarios.Audio":[97],"demos":[98],"are":[99],"available":[100],"at":[101],"wavegrad.github.io/specgrad/.":[102]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":15}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}