{"id":"https://openalex.org/W4408356205","doi":"https://doi.org/10.1109/icassp49660.2025.10887810","title":"Investigation of perceptual music similarity focusing on each instrumental part","display_name":"Investigation of perceptual music similarity focusing on each instrumental part","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408356205","doi":"https://doi.org/10.1109/icassp49660.2025.10887810"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"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,Graduate School of Informatics,Nagoya,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Graduate School of Informatics,Nagoya,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":["Information Technology Center Nagoya University,Nagoya,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Center Nagoya University,Nagoya,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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9926000237464905,"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":0.9926000237464905,"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":0.9843999743461609,"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/similarity","display_name":"Similarity (geometry)","score":0.6679927110671997},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.598409116268158},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5789701342582703},{"id":"https://openalex.org/keywords/instrumental-music","display_name":"Instrumental music","score":0.4822879135608673},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4267690181732178},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4220176935195923},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33357274532318115},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.24608632922172546},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.18380069732666016},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.13375705480575562},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.06655502319335938},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.054292917251586914}],"concepts":[{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6679927110671997},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.598409116268158},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5789701342582703},{"id":"https://openalex.org/C2993931450","wikidata":"https://www.wikidata.org/wiki/Q639197","display_name":"Instrumental music","level":3,"score":0.4822879135608673},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4267690181732178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4220176935195923},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33357274532318115},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.24608632922172546},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.18380069732666016},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.13375705480575562},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.06655502319335938},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.054292917251586914},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":23,"referenced_works":["https://openalex.org/W1915070853","https://openalex.org/W2099102094","https://openalex.org/W2101689211","https://openalex.org/W2130664550","https://openalex.org/W2155836578","https://openalex.org/W2163986931","https://openalex.org/W2165320163","https://openalex.org/W2591719913","https://openalex.org/W2963258075","https://openalex.org/W2998490864","https://openalex.org/W3009221956","https://openalex.org/W3135221267","https://openalex.org/W4312120967","https://openalex.org/W6600917420","https://openalex.org/W6674359587","https://openalex.org/W6675362077","https://openalex.org/W6696901769","https://openalex.org/W6704025895","https://openalex.org/W6745586488","https://openalex.org/W6765018989","https://openalex.org/W6765174816","https://openalex.org/W6781913179","https://openalex.org/W6864351101"],"related_works":["https://openalex.org/W140599881","https://openalex.org/W2386544682","https://openalex.org/W325310675","https://openalex.org/W2591707970","https://openalex.org/W15045666","https://openalex.org/W2565390241","https://openalex.org/W4230782429","https://openalex.org/W16358045","https://openalex.org/W2283601240","https://openalex.org/W2495481631"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3,25,44],"investigation":[4],"of":[5,39,59,82,127],"perceptual":[6,37,64,91,118,141],"similarity":[7,38,65,93,120,135,142],"between":[8],"music":[9,27,50,92,119,134],"tracks":[10,42,51],"focusing":[11],"on":[12,18,69,96,102,116,143],"each":[13,104],"individual":[14],"instrumental":[15,98],"part":[16,99],"based":[17,68],"a":[19,113],"large-scale":[20],"listening":[21,31,84],"test":[22,57,85],"towards":[23],"developing":[24],"instrumental-part-based":[26],"retrieval.":[28],"In":[29],"the":[30,36,40,49,56,60,80,83,117,125,131,140],"test,":[32],"586":[33],"subjects":[34],"evaluate":[35],"audio":[41],"through":[43],"ABX":[45],"test.":[46],"We":[47,77],"use":[48],"and":[52,75,86,108,129],"their":[53],"stems":[54],"in":[55],"set":[58],"slakh2100":[61],"dataset.":[62],"The":[63],"is":[66,100],"evaluated":[67],"four":[70],"perspectives:":[71],"timbre,":[72],"rhythm,":[73],"melody,":[74],"overall.":[76],"have":[78,87,112],"analyzed":[79],"results":[81],"found":[88],"that":[89],"1)":[90],"varies":[94],"depending":[95],"which":[97],"focused":[101],"within":[103],"track;":[105],"2)":[106],"rhythm":[107],"melody":[109,126],"tend":[110,137],"to":[111,138],"larger":[114],"impact":[115],"than":[121],"timbre":[122,144],"except":[123],"for":[124],"drums;":[128],"3)":[130],"previously":[132],"proposed":[133],"features":[136],"capture":[139],"mainly.":[145]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
