{"id":"https://openalex.org/W4316660651","doi":"https://doi.org/10.1109/taslp.2023.3237161","title":"Improving Semi-Supervised Differentiable Synthesizer Sound Matching for Practical Applications","display_name":"Improving Semi-Supervised Differentiable Synthesizer Sound Matching for Practical Applications","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4316660651","doi":"https://doi.org/10.1109/taslp.2023.3237161"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3237161","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3237161","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/10017350.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/10017350.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086267956","display_name":"Naotake Masuda","orcid":"https://orcid.org/0000-0001-8064-3038"},"institutions":[{"id":"https://openalex.org/I14396692","display_name":"Tokyo University of Information Sciences","ror":"https://ror.org/044bdx604","country_code":"JP","type":"education","lineage":["https://openalex.org/I14396692"]},{"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":"Naotake Masuda","raw_affiliation_strings":["Department of Electrical Engineering and Information Systems, Graduate School of Engineering, The University of Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8064-3038","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Information Systems, Graduate School of Engineering, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I14396692","https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010715755","display_name":"Daisuke Saito","orcid":"https://orcid.org/0000-0003-3012-1607"},"institutions":[{"id":"https://openalex.org/I14396692","display_name":"Tokyo University of Information Sciences","ror":"https://ror.org/044bdx604","country_code":"JP","type":"education","lineage":["https://openalex.org/I14396692"]},{"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":"Daisuke Saito","raw_affiliation_strings":["Department of Electrical Engineering and Information Systems, Graduate School of Engineering, The University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Information Systems, Graduate School of Engineering, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I14396692","https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0877,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.87470267,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"31","issue":null,"first_page":"863","last_page":"875"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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/T11309","display_name":"Music and Audio Processing","score":1.0,"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/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/T11349","display_name":"Music Technology and Sound Studies","score":0.9994000196456909,"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/computer-science","display_name":"Computer science","score":0.7791751623153687},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5377504825592041},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4860420823097229},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.47185608744621277},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.43751275539398193},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.435660719871521},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30218011140823364}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7791751623153687},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5377504825592041},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4860420823097229},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.47185608744621277},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.43751275539398193},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.435660719871521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30218011140823364},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3237161","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3237161","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/10017350.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2023.3237161","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3237161","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/10017350.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4316660651.pdf","grobid_xml":"https://content.openalex.org/works/W4316660651.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W1546379016","https://openalex.org/W1731081199","https://openalex.org/W1971742329","https://openalex.org/W1998446618","https://openalex.org/W2127302078","https://openalex.org/W2221409856","https://openalex.org/W2345690065","https://openalex.org/W2791716806","https://openalex.org/W2890043615","https://openalex.org/W2939574508","https://openalex.org/W2962721334","https://openalex.org/W2962866891","https://openalex.org/W2963527086","https://openalex.org/W2977593013","https://openalex.org/W2977735357","https://openalex.org/W2984353870","https://openalex.org/W2998588915","https://openalex.org/W3039883906","https://openalex.org/W3162289111","https://openalex.org/W3167389445","https://openalex.org/W3185737013","https://openalex.org/W3215457199","https://openalex.org/W4285367200","https://openalex.org/W4285367203","https://openalex.org/W4309117899","https://openalex.org/W6605110445","https://openalex.org/W6618372016","https://openalex.org/W6634367950","https://openalex.org/W6637618735","https://openalex.org/W6638167735","https://openalex.org/W6696768903","https://openalex.org/W6697058068","https://openalex.org/W6711609916","https://openalex.org/W6712857557","https://openalex.org/W6736723571","https://openalex.org/W6742209995","https://openalex.org/W6754551998","https://openalex.org/W6771763809","https://openalex.org/W6782116033","https://openalex.org/W6784488536","https://openalex.org/W6787485125","https://openalex.org/W6798451072","https://openalex.org/W6803922201","https://openalex.org/W6811204662"],"related_works":["https://openalex.org/W1954884171","https://openalex.org/W1987537206","https://openalex.org/W2386387936","https://openalex.org/W2368779261","https://openalex.org/W2353463996","https://openalex.org/W2116708029","https://openalex.org/W3122531224","https://openalex.org/W2094368311","https://openalex.org/W2778699561","https://openalex.org/W1576518944"],"abstract_inverted_index":{"While":[0],"synthesizers":[1],"have":[2,61],"become":[3],"commonplace":[4],"in":[5,173],"music":[6],"production,":[7],"many":[8],"users":[9],"find":[10],"it":[11],"difficult":[12],"to":[13,20,29,40,54,168,192,232,243],"control":[14],"the":[15,31,33,55,79,92,101,113,121,138,142,146,150,170,210,234,247],"parameters":[16,43,77,161],"of":[17,75,86,96],"a":[18,22,46,84,110,116,193,205],"synthesizer":[19,102,122,186,196],"create":[21],"sound":[23,47,117,144],"as":[24,50,52,106],"they":[25],"intended.":[26],"In":[27,109,179],"order":[28],"assist":[30],"user,":[32],"<italic":[34],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[35],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">sound":[36],"matching</i>":[37],"task":[38],"aims":[39],"estimate":[41],"synthesis":[42,76,87,160],"that":[44,48,224,240],"produce":[45],"is":[49,123,212,230],"close":[51],"possible":[53],"query":[56,90],"sound.":[57,148],"Recently,":[58],"neural":[59,68],"networks":[60,69],"been":[62],"employed":[63],"for":[64],"this":[65,180,190,228],"task.":[66],"These":[67],"are":[70,162],"trained":[71,134,154,214,226],"on":[72,155],"paired":[73],"data":[74],"and":[78,145,176,188,200,219],"corresponding":[80],"output":[81,103,147],"sound,":[82],"optimizing":[83,137],"loss":[85,218,245],"parameters.":[88],"However,":[89],"by":[91,135],"user":[93],"usually":[94],"consists":[95],"real-world":[97,156],"sounds,":[98],"different":[99,185],"from":[100],"sounds":[104,157],"used":[105],"training":[107,207],"data.":[108],"previous":[111],"work,":[112,181],"authors":[114],"presented":[115],"matching":[118],"method":[119,165],"where":[120,209],"implemented":[124],"using":[125,215,227],"differentiable":[126],"DSP.":[127],"The":[128],"estimator":[129],"network":[130,151,211],"could":[131,152],"then":[132],"be":[133,153],"directly":[136],"spectral":[139,220,244],"similarity":[140],"between":[141],"original":[143],"Furthermore,":[149],"whose":[158],"ground-truth":[159],"unavailable.":[163],"This":[164],"was":[166],"shown":[167],"improve":[169],"match":[171],"quality":[172],"both":[174,216],"objective":[175],"subjective":[177],"measures.":[178],"we":[182],"experiment":[183],"with":[184,197],"configurations":[187],"extend":[189],"approach":[191],"more":[194],"practical":[195],"effect":[198,236],"modules":[199],"envelope":[201],"generators.":[202],"We":[203,222],"propose":[204],"novel":[206],"strategy":[208,229],"fully":[213],"parameter":[217],"loss.":[221],"show":[223],"models":[225,239],"able":[231],"utilize":[233],"chorus":[235,248],"effectively":[237],"while":[238],"switch":[241],"completely":[242],"underutilizes":[246],"effect.":[249]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}