{"id":"https://openalex.org/W4387870414","doi":"https://doi.org/10.1109/mlsp55844.2023.10285863","title":"Exploiting Music Source Separation For Singing Voice Detection","display_name":"Exploiting Music Source Separation For Singing Voice Detection","publication_year":2023,"publication_date":"2023-09-17","ids":{"openalex":"https://openalex.org/W4387870414","doi":"https://doi.org/10.1109/mlsp55844.2023.10285863"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp55844.2023.10285863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp55844.2023.10285863","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5093111485","display_name":"Francesco Bonzi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Francesco Bonzi","raw_affiliation_strings":["Musixmatch"],"affiliations":[{"raw_affiliation_string":"Musixmatch","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076690986","display_name":"Michele Mancusi","orcid":"https://orcid.org/0000-0003-1591-7076"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Michele Mancusi","raw_affiliation_strings":["Sapienza University of Rome"],"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110591047","display_name":"Simone Del Deo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simone Del Deo","raw_affiliation_strings":["Musixmatch"],"affiliations":[{"raw_affiliation_string":"Musixmatch","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093111486","display_name":"Pierfrancesco Melucci","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pierfrancesco Melucci","raw_affiliation_strings":["Musixmatch"],"affiliations":[{"raw_affiliation_string":"Musixmatch","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006447756","display_name":"Maria Stella Tavella","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maria Stella Tavella","raw_affiliation_strings":["Musixmatch"],"affiliations":[{"raw_affiliation_string":"Musixmatch","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068179626","display_name":"Loreto Parisi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Loreto Parisi","raw_affiliation_strings":["Musixmatch"],"affiliations":[{"raw_affiliation_string":"Musixmatch","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087051832","display_name":"Emanuele Rodol\u00e0","orcid":"https://orcid.org/0000-0003-0091-7241"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Emanuele Rodol\u00e1","raw_affiliation_strings":["Sapienza University of Rome"],"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome","institution_ids":["https://openalex.org/I861853513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5093111485"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4066,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.58408963,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"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":1.0,"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":1.0,"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/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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962000250816345,"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/source-separation","display_name":"Source separation","score":0.800434410572052},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.7602099180221558},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6503005027770996},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5589750409126282},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5312399864196777},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2886967658996582},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.060709238052368164}],"concepts":[{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.800434410572052},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7602099180221558},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6503005027770996},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5589750409126282},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5312399864196777},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2886967658996582},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.060709238052368164},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp55844.2023.10285863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp55844.2023.10285863","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1485009520","https://openalex.org/W1583001605","https://openalex.org/W2052675777","https://openalex.org/W2098796164","https://openalex.org/W2154591323","https://openalex.org/W2207196656","https://openalex.org/W2406222150","https://openalex.org/W2408239454","https://openalex.org/W2414894569","https://openalex.org/W2604959036","https://openalex.org/W2964235767","https://openalex.org/W2990594533","https://openalex.org/W3083502750","https://openalex.org/W3094502228","https://openalex.org/W3192610910","https://openalex.org/W3213726885","https://openalex.org/W4226300471","https://openalex.org/W4285261371","https://openalex.org/W4385245566","https://openalex.org/W6628877408","https://openalex.org/W6715395060","https://openalex.org/W6736327223","https://openalex.org/W6739901393","https://openalex.org/W6752254909","https://openalex.org/W6784333009"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W2376664795","https://openalex.org/W2077498359"],"abstract_inverted_index":{"Singing":[0],"voice":[1],"detection":[2],"(SVD)":[3],"is":[4],"an":[5],"essential":[6],"task":[7],"in":[8],"many":[9,33],"music":[10,46,73],"information":[11],"retrieval":[12],"(MIR)":[13],"applications.":[14],"Deep":[15],"learning":[16,93],"methods":[17],"have":[18],"shown":[19],"promising":[20],"results":[21],"for":[22,84,91,132],"SVD,":[23],"but":[24],"further":[25],"performance":[26,98,115],"improvements":[27],"are":[28],"desirable":[29],"since":[30],"it":[31],"underlies":[32],"other":[34],"tasks.":[35],"This":[36],"work":[37,64],"proposes":[38],"a":[39,44,60,72,121],"novel":[40],"SVD":[41,86],"system":[42],"combining":[43],"state-of-the-art":[45,131],"source":[47,74],"separator":[48],"(Demucs)":[49],"with":[50],"two":[51,66,118],"downstream":[52],"models:":[53],"Long-term":[54],"Recurrent":[55],"Convolutional":[56],"Network":[57],"(LRCN)":[58],"and":[59,80,88,110,112,128],"Transformer":[61],"network.":[62],"Our":[63],"highlights":[65],"main":[67],"aspects:":[68],"the":[69,85,89,96,114,117,129,133],"impact":[70],"of":[71,116],"separation":[75],"model,":[76],"such":[77],"as":[78],"Demucs,":[79],"its":[81],"zero-shot":[82],"capabilities":[83],"task;":[87],"potential":[90],"deep":[92],"to":[94,120],"improve":[95],"system\u2019s":[97],"further.":[99],"We":[100],"evaluate":[101],"our":[102],"approach":[103],"on":[104],"three":[105],"datasets":[106],"(Jamendo":[107],"Corpus,":[108],"MedleyDB,":[109],"MIR-IK)":[111],"compare":[113],"models":[119],"baseline":[122],"root":[123],"mean":[124],"square":[125],"(RMS)":[126],"algorithm":[127],"current":[130],"Jamendo":[134],"Corpus":[135],"dataset.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}