{"id":"https://openalex.org/W4406860615","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849029","title":"Multi-Task Learning Approaches for Music Similarity Representation Learning Based on Individual Instrument Sounds","display_name":"Multi-Task Learning Approaches for Music Similarity Representation Learning Based on Individual Instrument Sounds","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406860615","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849029"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10849029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"conference-paper","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":null,"display_name":"Takehiro Imamura","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takehiro Imamura","raw_affiliation_strings":["Nagoya University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015108496","display_name":"Yuka Hashizume","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuka Hashizume","raw_affiliation_strings":["Nagoya University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9976999759674072,"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":0.9976999759674072,"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":0.9815999865531921,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9344000220298767,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.728382408618927},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7019056081771851},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6594588756561279},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5766909718513489},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4984595775604248},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45814722776412964},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.43000033497810364},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40776723623275757},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.355074018239975},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09865090250968933},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06431323289871216}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.728382408618927},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7019056081771851},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6594588756561279},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5766909718513489},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4984595775604248},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45814722776412964},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.43000033497810364},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40776723623275757},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.355074018239975},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09865090250968933},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06431323289871216},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10849029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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":15,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2100235918","https://openalex.org/W2104352833","https://openalex.org/W2133824856","https://openalex.org/W2963258075","https://openalex.org/W2963992487","https://openalex.org/W3009221956","https://openalex.org/W3015829441","https://openalex.org/W3037149862","https://openalex.org/W3135221267","https://openalex.org/W3159203726","https://openalex.org/W3162583214","https://openalex.org/W4312120967","https://openalex.org/W6631190155","https://openalex.org/W6746914816"],"related_works":["https://openalex.org/W2237537322","https://openalex.org/W2950678851","https://openalex.org/W4301248618","https://openalex.org/W2165343651","https://openalex.org/W2343790552","https://openalex.org/W2242427765","https://openalex.org/W2075830955","https://openalex.org/W2951720331","https://openalex.org/W4309969809","https://openalex.org/W3111398917"],"abstract_inverted_index":{"Music":[0],"similarity":[1,54,68,129,148,160],"representation":[2],"learning":[3,107,142,182],"(MSRL)":[4],"based":[5,143,153],"on":[6,30,85,144,154],"individual":[7],"instrument":[8,59],"sounds":[9],"(InMSRL)":[10],"is":[11,93,185],"a":[12,17,73,78],"potential":[13],"technique":[14],"to":[15,28,96,109,112,188],"develop":[16],"new":[18],"function":[19],"in":[20,76,90,192],"music":[21,35,48,53,67,128,147,159],"recommendation":[22],"and":[23,52,61,89,126,151,166,196],"retrieval":[24],"systems,":[25],"allowing":[26],"users":[27],"focus":[29],"multiple":[31],"partial":[32],"elements":[33],"of":[34,122],"pieces.":[36],"There":[37],"have":[38],"been":[39],"proposed":[40],"two":[41],"main":[42],"approaches,":[43],"Cascade":[44,174,198],"that":[45,63,168],"sequentially":[46],"performs":[47],"source":[49],"separation":[50,79,135],"(MSS)":[51],"feature":[55,87,130,149,194],"extraction":[56,150],"for":[57,173,183],"each":[58],"sound":[60],"Direct":[62,184,204],"directly":[64],"extracts":[65],"disentangled":[66,99,146,158],"features.":[69,100,161],"Each":[70],"approach":[71],"has":[72],"specific":[74],"problem;":[75],"Cascade,":[77,117],"error":[80],"often":[81],"causes":[82],"adverse":[83],"effects":[84],"the":[86,123,127,145,157,170,180,193,200,206],"extraction;":[88],"Direct,":[91,138],"it":[92],"usually":[94],"hard":[95],"learn":[97],"accurately":[98],"In":[101],"this":[102],"paper,":[103],"we":[104,118,139],"propose":[105,119,140],"multi-task":[106,141,181,207],"approaches":[108],"leveraging":[110],"MSS":[111,124,152],"address":[113],"these":[114],"issues.":[115],"For":[116,137],"end-to-end":[120,171,201],"fine-tuning":[121,172,202],"model":[125],"extractors":[131],"using":[132],"an":[133],"auxiliary":[134],"loss.":[136],"reconstruction":[155],"with":[156,199,205],"We":[162],"conduct":[163],"experimental":[164],"evaluations":[165],"demonstrate":[167],"1)":[169],"significantly":[175],"improves":[176],"InMSRL":[177],"performance,":[178],"2)":[179],"also":[186],"helpful":[187],"improve":[189],"disentanglement":[190],"performance":[191],"extraction,":[195],"3)":[197],"outperforms":[203],"learning.":[208]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}