{"id":"https://openalex.org/W4403182822","doi":"https://doi.org/10.1109/is262782.2024.10704147","title":"Benchmarking Music Demixing Models for Deep Drum Source Separation","display_name":"Benchmarking Music Demixing Models for Deep Drum Source Separation","publication_year":2024,"publication_date":"2024-09-30","ids":{"openalex":"https://openalex.org/W4403182822","doi":"https://doi.org/10.1109/is262782.2024.10704147"},"language":"en","primary_location":{"id":"doi:10.1109/is262782.2024.10704147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/is262782.2024.10704147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 5th International Symposium on the Internet of Sounds (IS2)","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/A5000588289","display_name":"Alessandro Ilic Mezza","orcid":"https://orcid.org/0000-0002-9438-3190"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Alessandro Ilic Mezza","raw_affiliation_strings":["DEIB, Politecnico di Milano,Milan,Italy","DEIB, Politecnico di Milano, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"DEIB, Politecnico di Milano,Milan,Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"DEIB, Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049892617","display_name":"Riccardo Giampiccolo","orcid":"https://orcid.org/0000-0001-6144-8288"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Riccardo Giampiccolo","raw_affiliation_strings":["DEIB, Politecnico di Milano,Milan,Italy","DEIB, Politecnico di Milano, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"DEIB, Politecnico di Milano,Milan,Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"DEIB, Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088704369","display_name":"Alberto Bernardini","orcid":"https://orcid.org/0000-0001-7973-0134"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alberto Bernardini","raw_affiliation_strings":["DEIB, Politecnico di Milano,Milan,Italy","DEIB, Politecnico di Milano, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"DEIB, Politecnico di Milano,Milan,Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"DEIB, Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051897828","display_name":"Augusto Sarti","orcid":"https://orcid.org/0000-0002-5803-1702"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Augusto Sarti","raw_affiliation_strings":["DEIB, Politecnico di Milano,Milan,Italy","DEIB, Politecnico di Milano, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"DEIB, Politecnico di Milano,Milan,Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"DEIB, Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5000588289"],"corresponding_institution_ids":["https://openalex.org/I93860229"],"apc_list":null,"apc_paid":null,"fwci":0.3735,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57605611,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"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":0.9998000264167786,"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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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/benchmarking","display_name":"Benchmarking","score":0.7559329271316528},{"id":"https://openalex.org/keywords/drum","display_name":"Drum","score":0.7305548191070557},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5842975378036499},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.48824456334114075},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.44452497363090515},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38775870203971863},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.11419501900672913},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.10802462697029114},{"id":"https://openalex.org/keywords/archaeology","display_name":"Archaeology","score":0.07667461037635803}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7559329271316528},{"id":"https://openalex.org/C175845324","wikidata":"https://www.wikidata.org/wiki/Q2738285","display_name":"Drum","level":2,"score":0.7305548191070557},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5842975378036499},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.48824456334114075},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.44452497363090515},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38775870203971863},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.11419501900672913},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.10802462697029114},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.07667461037635803},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/is262782.2024.10704147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/is262782.2024.10704147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 5th International Symposium on the Internet of Sounds (IS2)","raw_type":"proceedings-article"},{"id":"pmh:oai:re.public.polimi.it:11311/1274936","is_oa":false,"landing_page_url":"https://hdl.handle.net/11311/1274936","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W202885422","https://openalex.org/W398859631","https://openalex.org/W651209258","https://openalex.org/W2025758844","https://openalex.org/W2106582496","https://openalex.org/W2381486035","https://openalex.org/W2560180317","https://openalex.org/W2801401223","https://openalex.org/W2892844477","https://openalex.org/W2990594533","https://openalex.org/W3037149862","https://openalex.org/W3094893721","https://openalex.org/W3124719842","https://openalex.org/W3199957557","https://openalex.org/W3216004336","https://openalex.org/W4226300471","https://openalex.org/W4245692952","https://openalex.org/W4323519173","https://openalex.org/W4372260250","https://openalex.org/W4375928773","https://openalex.org/W4376632818","https://openalex.org/W4388979610","https://openalex.org/W4389296752","https://openalex.org/W4389302098","https://openalex.org/W4392903379","https://openalex.org/W4392903460","https://openalex.org/W4394916053","https://openalex.org/W4396634099","https://openalex.org/W6712990308","https://openalex.org/W6762661407","https://openalex.org/W6767440493","https://openalex.org/W6784335252","https://openalex.org/W7043642130"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2000169967","https://openalex.org/W2077498359"],"abstract_inverted_index":{"Traditionally,":[0],"drum":[1,25,72,98,110,136],"source":[2,54,73,111],"separation":[3],"has":[4],"been":[5],"tack-led":[6],"using":[7,90],"nonnegative":[8],"spectro-temporal":[9],"factorization":[10],"methods.":[11],"Only":[12],"recently,":[13],"deep":[14,71],"learning":[15],"showed":[16],"unprecedented":[17],"performance":[18,123],"in":[19,49],"separating":[20],"five":[21],"stems":[22],"from":[23],"a":[24,41,61,77,92],"mixture,":[26],"namely,":[27],"kick":[28],"drum,":[29,31],"snare":[30],"toms,":[32],"hi-hat,":[33],"and":[34,87,117,124,131,151],"cymbals.":[35],"The":[36],"literature,":[37],"however,":[38],"still":[39],"lacks":[40],"thorough":[42],"comparison":[43],"of":[44,52,65,79,95],"the":[45,50,106],"techniques":[46],"readily":[47],"available":[48],"context":[51],"music":[53,66,147,153],"separation.":[55,74],"In":[56],"this":[57],"paper,":[58],"we":[59,113],"conduct":[60],"first":[62],"benchmarking":[63],"analysis":[64],"demixing":[67,137],"models":[68,138],"tailored":[69],"for":[70,109,129,139],"We":[75],"evaluate":[76],"range":[78],"state-of-the-art":[80,107],"neural":[81],"network":[82],"architectures,":[83],"including":[84],"HT-Demucs,":[85],"MDX23C,":[86],"BS-RoFormer,":[88],"trained":[89],"StemGMD,":[91],"large-scale":[93],"dataset":[94],"isolated":[96],"single-instrument":[97],"stems.":[99],"Besides":[100],"demonstrating":[101],"that":[102],"said":[103],"architectures":[104],"out-perform":[105],"method":[108],"separation,":[112],"discuss":[114],"their":[115,122],"strengths":[116],"weaknesses,":[118],"giving":[119],"insights":[120],"into":[121],"ultimately":[125],"offering":[126],"valuable":[127],"guidance":[128],"researchers":[130],"practitioners":[132],"willing":[133],"to":[134,146],"develop":[135],"different":[140],"applications,":[141],"among":[142],"which":[143],"those":[144],"related":[145],"making,":[148],"personalized":[149],"listening,":[150],"online":[152],"education":[154],"stand":[155],"out.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
