{"id":"https://openalex.org/W4225300994","doi":"https://doi.org/10.1109/icassp43922.2022.9746399","title":"Differentiable Digital Signal Processing Mixture Model for Synthesis Parameter Extraction from Mixture of Harmonic Sounds","display_name":"Differentiable Digital Signal Processing Mixture Model for Synthesis Parameter Extraction from Mixture of Harmonic Sounds","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225300994","doi":"https://doi.org/10.1109/icassp43922.2022.9746399"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746399","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746399","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/A5103833453","display_name":"Masaya Kawamura","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Masaya Kawamura","raw_affiliation_strings":["The University of Tokyo,Tokyo,Japan","The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102941659","display_name":"Tomohiko Nakamura","orcid":"https://orcid.org/0000-0003-4385-7170"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiko Nakamura","raw_affiliation_strings":["The University of Tokyo,Tokyo,Japan","The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071479017","display_name":"Daichi Kitamura","orcid":"https://orcid.org/0000-0003-1117-7939"},"institutions":[{"id":"https://openalex.org/I4210160866","display_name":"National Institute of Technology, Kagawa College","ror":"https://ror.org/04xfwhf17","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210120810","https://openalex.org/I4210160866"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daichi Kitamura","raw_affiliation_strings":["National Institute of Technology,Kagawa College,Kagawa,Japan","Kagawa College, National Institute of Technology, Kagawa, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Technology,Kagawa College,Kagawa,Japan","institution_ids":["https://openalex.org/I4210160866"]},{"raw_affiliation_string":"Kagawa College, National Institute of Technology, Kagawa, Japan","institution_ids":["https://openalex.org/I4210160866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003814223","display_name":"Hiroshi Saruwatari","orcid":"https://orcid.org/0000-0003-0876-5617"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Saruwatari","raw_affiliation_strings":["The University of Tokyo,Tokyo,Japan","The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079456672","display_name":"Yu Takahashi","orcid":"https://orcid.org/0000-0002-3066-9501"},"institutions":[{"id":"https://openalex.org/I1295929820","display_name":"Yamaha (Japan)","ror":"https://ror.org/05s7fvh27","country_code":"JP","type":"company","lineage":["https://openalex.org/I1295929820"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yu Takahashi","raw_affiliation_strings":["Yamaha Corporation,Shizuoka,Japan","Yamaha Corporation, Shizuoka, Japan"],"affiliations":[{"raw_affiliation_string":"Yamaha Corporation,Shizuoka,Japan","institution_ids":["https://openalex.org/I1295929820"]},{"raw_affiliation_string":"Yamaha Corporation, Shizuoka, Japan","institution_ids":["https://openalex.org/I1295929820"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021841017","display_name":"Kazunobu Kondo","orcid":"https://orcid.org/0000-0001-7428-696X"},"institutions":[{"id":"https://openalex.org/I1295929820","display_name":"Yamaha (Japan)","ror":"https://ror.org/05s7fvh27","country_code":"JP","type":"company","lineage":["https://openalex.org/I1295929820"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazunobu Kondo","raw_affiliation_strings":["Yamaha Corporation,Shizuoka,Japan","Yamaha Corporation, Shizuoka, Japan"],"affiliations":[{"raw_affiliation_string":"Yamaha Corporation,Shizuoka,Japan","institution_ids":["https://openalex.org/I1295929820"]},{"raw_affiliation_string":"Yamaha Corporation, Shizuoka, Japan","institution_ids":["https://openalex.org/I1295929820"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103833453"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":1.0933,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.78816494,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"941","last_page":"945"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9965999722480774,"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/autoencoder","display_name":"Autoencoder","score":0.6653324365615845},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.6441571116447449},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6155092716217041},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5772775411605835},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.5387613773345947},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4785350263118744},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4753819704055786},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4530671238899231},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.448526531457901},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.44450613856315613},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.43679261207580566},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42296499013900757},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.41402214765548706},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3776034116744995},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.37431347370147705},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.3014070391654968},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2332107424736023}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6653324365615845},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.6441571116447449},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6155092716217041},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5772775411605835},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.5387613773345947},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4785350263118744},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4753819704055786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4530671238899231},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.448526531457901},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.44450613856315613},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.43679261207580566},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42296499013900757},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.41402214765548706},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3776034116744995},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.37431347370147705},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3014070391654968},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2332107424736023},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746399","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746399","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W141230911","https://openalex.org/W1966815568","https://openalex.org/W2051586096","https://openalex.org/W2088432713","https://openalex.org/W2142978829","https://openalex.org/W2560254426","https://openalex.org/W2759171953","https://openalex.org/W2764251778","https://openalex.org/W2765811365","https://openalex.org/W2906214917","https://openalex.org/W2962866891","https://openalex.org/W2963992487","https://openalex.org/W2981851635","https://openalex.org/W2994822369","https://openalex.org/W3000389243","https://openalex.org/W3015287975","https://openalex.org/W3081837312","https://openalex.org/W3095303521","https://openalex.org/W3095999710","https://openalex.org/W3101943858","https://openalex.org/W3104539075","https://openalex.org/W3116770123","https://openalex.org/W3136272958","https://openalex.org/W3160751854","https://openalex.org/W3170094039","https://openalex.org/W4287683335","https://openalex.org/W4287688400","https://openalex.org/W4297817572","https://openalex.org/W4362724041","https://openalex.org/W6605679885","https://openalex.org/W6745704996","https://openalex.org/W6755257315","https://openalex.org/W6771763809","https://openalex.org/W6781725382","https://openalex.org/W6782116033","https://openalex.org/W6782757012","https://openalex.org/W6788137280","https://openalex.org/W6796762324","https://openalex.org/W6798451072"],"related_works":["https://openalex.org/W4283026649","https://openalex.org/W4378498754","https://openalex.org/W2289868279","https://openalex.org/W4254916641","https://openalex.org/W1546240199","https://openalex.org/W2109142991","https://openalex.org/W3112881379","https://openalex.org/W2002298560","https://openalex.org/W2019256813","https://openalex.org/W2158216966"],"abstract_inverted_index":{"A":[0],"differentiable":[1],"digital":[2],"signal":[3],"processing":[4],"(DDSP)":[5],"autoencoder":[6,134],"is":[7,48],"a":[8,14,51,67,74,127],"musical":[9],"sound":[10,54],"synthesizer":[11],"that":[12,72,116,130],"combines":[13],"deep":[15],"neural":[16],"network":[17],"(DNN)":[18],"and":[19,37,55,122],"spectral":[20],"modeling":[21],"synthesis.":[22],"It":[23],"allows":[24],"us":[25],"to":[26,95,135],"flexibly":[27],"edit":[28],"sounds":[29],"by":[30,139],"changing":[31],"the":[32,77,80,89,92,96,103,117,132,136],"fundamental":[33],"frequency,":[34],"timbre":[35],"feature,":[36],"loudness":[38],"(synthesis":[39],"parameters)":[40],"extracted":[41],"from":[42],"an":[43,140],"input":[44],"sound.":[45],"However,":[46],"it":[47],"designed":[49],"for":[50],"monophonic":[52],"harmonic":[53,60],"cannot":[56],"handle":[57],"mixtures":[58],"of":[59,79,82,91,106],"sounds.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65,99,114],"propose":[66],"model":[68,94],"(DDSP":[69],"mixture":[70,75],"model)":[71],"represents":[73],"as":[76],"sum":[78],"outputs":[81],"multiple":[83],"pretrained":[84],"DDSP":[85,133],"autoencoders.":[86],"By":[87],"fitting":[88],"output":[90],"proposed":[93,118],"observed":[97],"mixture,":[98],"can":[100],"directly":[101],"estimate":[102],"synthesis":[104,110],"parameters":[105],"each":[107],"source.":[108],"Through":[109],"parameter":[111],"extraction":[112],"experiments,":[113],"show":[115],"method":[119,129],"has":[120],"high":[121],"stable":[123],"performance":[124],"compared":[125],"with":[126],"straightforward":[128],"applies":[131],"signals":[137],"separated":[138],"audio":[141],"source":[142],"separation":[143],"method.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}