{"id":"https://openalex.org/W3196783587","doi":"https://doi.org/10.1145/3460426.3463590","title":"Semi-supervised Many-to-many Music Timbre Transfer","display_name":"Semi-supervised Many-to-many Music Timbre Transfer","publication_year":2021,"publication_date":"2021-08-24","ids":{"openalex":"https://openalex.org/W3196783587","doi":"https://doi.org/10.1145/3460426.3463590","mag":"3196783587"},"language":"en","primary_location":{"id":"doi:10.1145/3460426.3463590","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460426.3463590","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimedia Retrieval","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/A5101867128","display_name":"Yuchen Chang","orcid":"https://orcid.org/0000-0002-8496-9577"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yu-Chen Chang","raw_affiliation_strings":["National Cheng Kung University, Tainan, Taiwan Roc"],"affiliations":[{"raw_affiliation_string":"National Cheng Kung University, Tainan, Taiwan Roc","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101536450","display_name":"Wen\u2010Cheng Chen","orcid":"https://orcid.org/0000-0002-5581-9991"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wen-Cheng Chen","raw_affiliation_strings":["National Cheng Kung University, Tainan, Taiwan Roc"],"affiliations":[{"raw_affiliation_string":"National Cheng Kung University, Tainan, Taiwan Roc","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029298215","display_name":"Min\u2010Chun Hu","orcid":"https://orcid.org/0000-0003-1917-2155"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Min-Chun Hu","raw_affiliation_strings":["National Tsing Hua University, Hsinchu, Taiwan Roc"],"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Hsinchu, Taiwan Roc","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101867128"],"corresponding_institution_ids":["https://openalex.org/I91807558"],"apc_list":null,"apc_paid":null,"fwci":0.7618,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.71034483,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"442","last_page":"446"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9930999875068665,"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":0.9926999807357788,"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/timbre","display_name":"Timbre","score":0.9388416409492493},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.8833599090576172},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8249430060386658},{"id":"https://openalex.org/keywords/midi","display_name":"MIDI","score":0.7476630806922913},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5671119689941406},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.523662269115448},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.517820417881012},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5086253881454468},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.4260571300983429},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.41615721583366394},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.416043221950531},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3549988865852356},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3224763870239258},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.18829074501991272},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.14405161142349243}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.9388416409492493},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8833599090576172},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8249430060386658},{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.7476630806922913},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5671119689941406},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.523662269115448},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.517820417881012},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5086253881454468},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.4260571300983429},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.41615721583366394},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.416043221950531},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3549988865852356},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3224763870239258},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.18829074501991272},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.14405161142349243},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3460426.3463590","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460426.3463590","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1604034532","https://openalex.org/W2120847449","https://openalex.org/W2407685581","https://openalex.org/W2475287302","https://openalex.org/W2603777577","https://openalex.org/W2760103357","https://openalex.org/W2884225676","https://openalex.org/W2962775980","https://openalex.org/W2962793481","https://openalex.org/W2963073614","https://openalex.org/W2963775347","https://openalex.org/W2963890275"],"related_works":["https://openalex.org/W3133630535","https://openalex.org/W2398084541","https://openalex.org/W4242364395","https://openalex.org/W2386555541","https://openalex.org/W3042962886","https://openalex.org/W2920621887","https://openalex.org/W2187442448","https://openalex.org/W889314198","https://openalex.org/W4285031015","https://openalex.org/W2580099843"],"abstract_inverted_index":{"This":[0],"work":[1],"presents":[2],"a":[3,15,56,77,127,131],"music":[4,16,27],"timbre":[5,28,36],"transfer":[6,11,29,37,123],"model":[7,32,119],"that":[8,117],"aims":[9],"to":[10,24],"the":[12,20,25,73,94,97,102,105,111],"style":[13,122],"of":[14,104],"clip":[17],"while":[18],"preserving":[19],"semantic":[21],"content.":[22],"Compared":[23],"existing":[26],"models,":[30],"our":[31,118],"can":[33,120],"achieve":[34,121],"many-to-many":[35],"between":[38],"different":[39],"instruments.":[40],"The":[41],"proposed":[42,106],"method":[43],"is":[44,83],"based":[45],"an":[46,64],"autoencoder":[47],"framework,":[48],"which":[49,82],"comprises":[50],"two":[51],"pretrained":[52],"encoders":[53],"trained":[54,62],"in":[55,63,126],"supervised":[57],"manner":[58,129],"and":[59,88,96],"one":[60],"decoder":[61],"unsupervised":[65],"manner.":[66],"To":[67,108],"learn":[68],"more":[69],"representative":[70],"features":[71],"for":[72],"encoders,":[74],"we":[75,114],"produced":[76],"parallel":[78,133],"dataset,":[79],"called":[80],"MI-Para,":[81],"synthesized":[84],"from":[85],"MIDI":[86],"files":[87],"digital":[89],"audio":[90],"workstations":[91],"(DAW).":[92],"Both":[93],"objective":[95],"subjective":[98],"evaluation":[99],"results":[100],"showed":[101],"effectiveness":[103],"framework.":[107],"scale":[109],"up":[110],"application":[112],"scenario,":[113],"also":[115],"demonstrate":[116],"by":[124],"training":[125],"semi-supervised":[128],"with":[130],"smaller":[132],"dataset.":[134]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}