{"id":"https://openalex.org/W4408354636","doi":"https://doi.org/10.1109/icassp49660.2025.10889959","title":"BeatKAN: An Efficient and Drum-Attuned Beat Tracking Method Using Kolmogorov-Arnold Networks","display_name":"BeatKAN: An Efficient and Drum-Attuned Beat Tracking Method Using Kolmogorov-Arnold Networks","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354636","doi":"https://doi.org/10.1109/icassp49660.2025.10889959"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889959","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889959","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":"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/A5100456083","display_name":"Zhicheng Zhang","orcid":"https://orcid.org/0000-0002-5333-1394"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhicheng Zhang","raw_affiliation_strings":["Fudan University,School of Computer Science and Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060139314","display_name":"Ganghui Ru","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ganghui Ru","raw_affiliation_strings":["Fudan University,School of Computer Science and Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100739392","display_name":"Wei Li","orcid":"https://orcid.org/0000-0002-4308-4385"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["Fudan University,School of Computer Science and Technology, Shanghai Key Laboratory of Intelligent Information Processing,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science and Technology, Shanghai Key Laboratory of Intelligent Information Processing,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100456083"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":2.5565,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.87331081,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"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":0.9977999925613403,"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":0.9977999925613403,"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":0.9955000281333923,"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":0.9581999778747559,"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/beat","display_name":"Beat (acoustics)","score":0.6527208089828491},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6228910684585571},{"id":"https://openalex.org/keywords/drum","display_name":"Drum","score":0.5343524217605591},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5081303119659424},{"id":"https://openalex.org/keywords/heart-beat","display_name":"Heart beat","score":0.4662778377532959},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41346490383148193},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3661259412765503},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.16161787509918213},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15620291233062744},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08409944176673889},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06145530939102173},{"id":"https://openalex.org/keywords/mechanical-engineering","display_name":"Mechanical engineering","score":0.05388224124908447}],"concepts":[{"id":"https://openalex.org/C189809214","wikidata":"https://www.wikidata.org/wiki/Q829522","display_name":"Beat (acoustics)","level":2,"score":0.6527208089828491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6228910684585571},{"id":"https://openalex.org/C175845324","wikidata":"https://www.wikidata.org/wiki/Q2738285","display_name":"Drum","level":2,"score":0.5343524217605591},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5081303119659424},{"id":"https://openalex.org/C2982892191","wikidata":"https://www.wikidata.org/wiki/Q253408","display_name":"Heart beat","level":2,"score":0.4662778377532959},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41346490383148193},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3661259412765503},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.16161787509918213},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15620291233062744},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08409944176673889},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06145530939102173},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.05388224124908447},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889959","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889959","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":29,"referenced_works":["https://openalex.org/W2016885049","https://openalex.org/W2117330939","https://openalex.org/W2133824856","https://openalex.org/W2156063659","https://openalex.org/W2404176928","https://openalex.org/W2572771584","https://openalex.org/W2903502793","https://openalex.org/W2908122412","https://openalex.org/W3170942659","https://openalex.org/W4224918587","https://openalex.org/W4280498166","https://openalex.org/W4312728222","https://openalex.org/W4372260188","https://openalex.org/W4372260250","https://openalex.org/W4386763510","https://openalex.org/W4389066209","https://openalex.org/W6631117800","https://openalex.org/W6697467378","https://openalex.org/W6713329139","https://openalex.org/W6732361153","https://openalex.org/W6740984418","https://openalex.org/W6746430418","https://openalex.org/W6756801033","https://openalex.org/W6770646036","https://openalex.org/W6844204944","https://openalex.org/W6866597880","https://openalex.org/W6867176674","https://openalex.org/W6869892494","https://openalex.org/W6941176339"],"related_works":["https://openalex.org/W2379304833","https://openalex.org/W2416864232","https://openalex.org/W2144144167","https://openalex.org/W2022012065","https://openalex.org/W2031066127","https://openalex.org/W3023842728","https://openalex.org/W569557334","https://openalex.org/W2618037398","https://openalex.org/W4300025576","https://openalex.org/W2092720438"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,43,60],"propose":[4],"an":[5],"efficient":[6,36],"and":[7,80],"drum-attuned":[8],"beat":[9,78,106],"tracking":[10],"method":[11],"based":[12],"on":[13,56],"Kolmogorov-Arnold":[14],"networks":[15],"(KAN).":[16],"Traditional":[17],"MLP-based":[18],"frameworks":[19],"struggle":[20],"with":[21],"complex":[22,40],"musical":[23],"signals":[24],"due":[25],"to":[26,38,46,66],"limited":[27],"capacity":[28],"in":[29,105],"modeling":[30],"intricate":[31],"patterns.":[32],"Inspired":[33],"by":[34,50],"KAN\u2019s":[35],"ability":[37],"capture":[39],"time-frequency":[41],"relationships,":[42],"leverage":[44],"it":[45],"enhance":[47],"our":[48,94],"model":[49],"employing":[51],"learnable":[52],"nonlinear":[53],"activation":[54],"functions":[55],"convolutional":[57],"kernels.":[58],"Additionally,":[59],"utilize":[61],"music":[62],"source":[63],"separation":[64],"techniques":[65],"extract":[67],"drum":[68,88],"tracks":[69],"from":[70],"the":[71,76,82,98],"original":[72],"audio,":[73],"thereby":[74],"expanding":[75],"existing":[77],"datasets":[79],"simulating":[81],"human":[83],"perception":[84],"of":[85],"beats":[86],"through":[87],"sounds.":[89],"Experimental":[90],"results":[91],"demonstrate":[92],"that":[93],"approach":[95],"significantly":[96],"reduces":[97],"parameter":[99],"count":[100],"while":[101],"maintaining":[102],"high":[103],"accuracy":[104],"tracking.":[107]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}
