{"id":"https://openalex.org/W4402980307","doi":"https://doi.org/10.1109/icme57554.2024.10688211","title":"Improving Drum Source Separation with Temporal-Frequency Statistical Descriptors","display_name":"Improving Drum Source Separation with Temporal-Frequency Statistical Descriptors","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402980307","doi":"https://doi.org/10.1109/icme57554.2024.10688211"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10688211","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10688211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5100391323","display_name":"Si Li","orcid":"https://orcid.org/0000-0002-5753-5976"},"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":"Si Li","raw_affiliation_strings":["Fudan University,School of Computer Science and Technology,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science and Technology,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107933093","display_name":"Jiaxing Liu","orcid":"https://orcid.org/0009-0002-0832-4985"},"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":"Jiaxing Liu","raw_affiliation_strings":["Fudan University,School of Computer Science and Technology,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science and Technology,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100723445","display_name":"Peilin Li","orcid":"https://orcid.org/0000-0001-9826-1206"},"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":"Peilin Li","raw_affiliation_strings":["Fudan University,School of Computer Science and Technology,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science and Technology,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087938991","display_name":"Dichucheng Li","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":"Dichucheng Li","raw_affiliation_strings":["Fudan University,School of Computer Science and Technology,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science and Technology,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101765236","display_name":"Xinlu Liu","orcid":"https://orcid.org/0000-0002-8560-2283"},"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":"Xinlu Liu","raw_affiliation_strings":["Fudan University,School of Computer Science and Technology,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science and Technology,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051966001","display_name":"Yongwei Gao","orcid":"https://orcid.org/0000-0001-7026-9273"},"institutions":[{"id":"https://openalex.org/I905225518","display_name":"Shanghai University of International Business and Economics","ror":"https://ror.org/031t68441","country_code":"CN","type":"education","lineage":["https://openalex.org/I905225518"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongwei Gao","raw_affiliation_strings":["Shanghai University of International Business and Economics,School of Statistics and Information,China"],"affiliations":[{"raw_affiliation_string":"Shanghai University of International Business and Economics,School of Statistics and Information,China","institution_ids":["https://openalex.org/I905225518"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100318193","display_name":"Wei Li","orcid":"https://orcid.org/0000-0002-4486-8341"},"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,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science and Technology,China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100391323"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18385266,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T10860","display_name":"Speech and Audio Processing","score":0.9980999827384949,"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/T10860","display_name":"Speech and Audio Processing","score":0.9980999827384949,"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":0.9855999946594238,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9771999716758728,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/drum","display_name":"Drum","score":0.6347317099571228},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6224904656410217},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5594084858894348},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5315318703651428},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.449435830116272},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4178483188152313},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.12153595685958862},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11419296264648438},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08295062184333801}],"concepts":[{"id":"https://openalex.org/C175845324","wikidata":"https://www.wikidata.org/wiki/Q2738285","display_name":"Drum","level":2,"score":0.6347317099571228},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6224904656410217},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5594084858894348},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5315318703651428},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.449435830116272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4178483188152313},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.12153595685958862},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11419296264648438},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08295062184333801},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10688211","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10688211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1509813908","https://openalex.org/W2031820693","https://openalex.org/W3024816962","https://openalex.org/W973023320","https://openalex.org/W1910172735","https://openalex.org/W2118307209","https://openalex.org/W2107364365","https://openalex.org/W2107688514","https://openalex.org/W2137288760","https://openalex.org/W3121710301"],"abstract_inverted_index":{"Drum":[0],"Source":[1],"Separation":[2],"(DSS)":[3],"aims":[4],"to":[5,31,71,92],"separate":[6,93],"drum":[7,11,62,94],"mixtures":[8],"into":[9],"individual":[10],"sounds,":[12],"such":[13],"as":[14],"kick":[15],"and":[16,38,46,65,89,113,126,131],"snare.":[17],"Deep":[18],"neural":[19],"network":[20],"methods":[21,49],"have":[22,51],"been":[23],"successfully":[24],"applied":[25],"for":[26],"source":[27],"separation.":[28],"However,":[29],"due":[30],"the":[32,39],"limited":[33],"size":[34],"of":[35,42,74,108],"existing":[36],"datasets":[37],"strongly":[40],"overlap":[41],"drums":[43],"in":[44,124],"frequency":[45],"time,":[47],"these":[48,56],"still":[50],"certain":[52],"shortcomings.":[53],"To":[54],"address":[55],"challenges,":[57],"we":[58],"construct":[59],"a":[60,67,105],"large":[61],"sound":[63],"dataset":[64,132],"propose":[66],"novel":[68],"training":[69,78],"objective":[70,79],"improve":[72],"performance":[73],"DSS":[75],"task.":[76],"The":[77],"leverages":[80],"three":[81],"temporal-frequency":[82],"statistical":[83],"descriptors":[84],"(spectral":[85],"centroid,":[86],"spectral":[87,90],"spread,":[88],"flux)":[91],"sources.":[95],"Our":[96,129],"experimental":[97],"results":[98],"demonstrate":[99],"that":[100],"our":[101,119],"method":[102,120],"can":[103],"make":[104],"SDR":[106],"improvement":[107],"0.98":[109],"dB":[110,115],"on":[111,116],"UNet":[112],"1.07":[114],"MERT.":[117],"Furthermore,":[118],"achieves":[121],"consistent":[122],"improvements":[123],"low-resource":[125],"cross-dataset":[127],"scenarios.":[128],"code":[130],"are":[133],"available":[134],"at":[135],"https://github.com/150042/Drum-Separation-TF.":[136]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}