{"id":"https://openalex.org/W4416800083","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249004","title":"Drum-to-Vocal Percussion Sound Conversion and Its Evaluation Methodology","display_name":"Drum-to-Vocal Percussion Sound Conversion and Its Evaluation Methodology","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416800083","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249004"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249004","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249004","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5120025434","display_name":"Rinka Nobukawa","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":"Rinka Nobukawa","raw_affiliation_strings":["University of Tokyo,Graduate School of Information Science and Technology,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"University of Tokyo,Graduate School of Information Science and Technology,Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040738489","display_name":"Makito Kitamura","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":false,"raw_author_name":"Makito Kitamura","raw_affiliation_strings":["University of Tokyo,Graduate School of Information Science and Technology,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"University of Tokyo,Graduate School of Information Science and Technology,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/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiko Nakamura","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST),Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST),Tokyo,Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013050263","display_name":"Shinnosuke Takamichi","orcid":"https://orcid.org/0000-0003-0520-7847"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinnosuke Takamichi","raw_affiliation_strings":["Keio University,Faculty of Science and Technology,Yokohama,Japan"],"affiliations":[{"raw_affiliation_string":"Keio University,Faculty of Science and Technology,Yokohama,Japan","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003247157","display_name":"Hiroshi Saruwatari","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":false,"raw_author_name":"Hiroshi Saruwatari","raw_affiliation_strings":["University of Tokyo,Graduate School of Information Science and Technology,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"University of Tokyo,Graduate School of Information Science and Technology,Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5120025434"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40739016,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"198","last_page":"203"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.6583999991416931,"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"}},"topics":[{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.6583999991416931,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.06040000170469284,"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":0.05860000103712082,"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/timbre","display_name":"Timbre","score":0.8521000146865845},{"id":"https://openalex.org/keywords/percussion","display_name":"Percussion","score":0.7832000255584717},{"id":"https://openalex.org/keywords/loudness","display_name":"Loudness","score":0.5414999723434448},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.5195000171661377},{"id":"https://openalex.org/keywords/headphones","display_name":"Headphones","score":0.4239000082015991},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.41679999232292175},{"id":"https://openalex.org/keywords/sound-recording-and-reproduction","display_name":"Sound recording and reproduction","score":0.41130000352859497},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.40799999237060547},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.38609999418258667}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.8521000146865845},{"id":"https://openalex.org/C81687914","wikidata":"https://www.wikidata.org/wiki/Q1501797","display_name":"Percussion","level":2,"score":0.7832000255584717},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7423999905586243},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5745000243186951},{"id":"https://openalex.org/C79018884","wikidata":"https://www.wikidata.org/wiki/Q622324","display_name":"Loudness","level":2,"score":0.5414999723434448},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.5195000171661377},{"id":"https://openalex.org/C2781258422","wikidata":"https://www.wikidata.org/wiki/Q186819","display_name":"Headphones","level":2,"score":0.4239000082015991},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.41679999232292175},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.41130000352859497},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.40799999237060547},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.38609999418258667},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.38519999384880066},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.38280001282691956},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.3573000133037567},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32690000534057617},{"id":"https://openalex.org/C2777185736","wikidata":"https://www.wikidata.org/wiki/Q7265603","display_name":"QUIET","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C89805583","wikidata":"https://www.wikidata.org/wiki/Q192940","display_name":"Accelerometer","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C2992428333","wikidata":"https://www.wikidata.org/wiki/Q11461","display_name":"Sound production","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.26980000734329224},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C2779864741","wikidata":"https://www.wikidata.org/wiki/Q4820027","display_name":"Auditory feedback","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.25870001316070557},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.2542000114917755},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249004","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249004","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":11,"referenced_works":["https://openalex.org/W1979099501","https://openalex.org/W2107860279","https://openalex.org/W2165817365","https://openalex.org/W2745818471","https://openalex.org/W2963800363","https://openalex.org/W3015338123","https://openalex.org/W3118335238","https://openalex.org/W3134950117","https://openalex.org/W4231284028","https://openalex.org/W4375869200","https://openalex.org/W4406461964"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"defines":[2],"the":[3,42,111,134],"novel":[4],"task":[5],"of":[6,44],"drum-to-vocal":[7],"percussion":[8,14],"(VP)":[9],"sound":[10],"conversion.":[11,141],"VP":[12,58,131],"imitates":[13],"instruments":[15],"through":[16],"human":[17],"vocalization":[18],"and":[19,35,41,71,89,118],"is":[20],"frequently":[21],"employed":[22],"in":[23],"contemporary":[24],"a":[25,61,107],"cappella":[26],"music.":[27],"It":[28],"exhibits":[29],"acoustic":[30],"properties":[31],"distinct":[32],"from":[33,65],"speech":[34,49],"singing":[36,51],"(e.g.,":[37],"aperiodicity,":[38],"noisy":[39],"transients,":[40],"absence":[43],"linguistic":[45],"structure),":[46],"making":[47],"conventional":[48],"or":[50],"synthesis":[52,59],"methods":[53,105,128],"unsuitable.":[54],"We":[55,93,100],"thus":[56],"formulate":[57],"as":[60,91],"timbre":[62],"transfer":[63],"problem":[64],"drum":[66],"sounds,":[67],"leveraging":[68],"their":[69],"rhythmic":[70,85],"timbral":[72,87],"correspondence.":[73],"To":[74],"support":[75],"this":[76],"formulation,":[77],"we":[78],"define":[79],"three":[80],"requirements":[81],"for":[82],"successful":[83],"conversion:":[84],"fidelity,":[86],"consistency,":[88],"naturalness":[90],"VP.":[92],"also":[94],"propose":[95],"corresponding":[96],"subjective":[97],"evaluation":[98],"criteria.":[99],"implement":[101],"two":[102],"baseline":[103],"conversion":[104],"using":[106],"neural":[108],"audio":[109,113],"synthesizer,":[110],"real-time":[112],"variational":[114],"autoencoder":[115],"(RAVE),":[116],"with":[117,133],"without":[119],"vector":[120],"quantization":[121],"(VQ).":[122],"Subjective":[123],"experiments":[124],"show":[125],"that":[126],"both":[127],"produce":[129],"plausible":[130],"outputs,":[132],"VQ-based":[135],"RAVE":[136],"model":[137],"yielding":[138],"more":[139],"consistent":[140]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}