{"id":"https://openalex.org/W4386763528","doi":"https://doi.org/10.1109/waspaa58266.2023.10248164","title":"A Novel Method to Detect Instrumental Music in a Large Scale Music Catalog","display_name":"A Novel Method to Detect Instrumental Music in a Large Scale Music Catalog","publication_year":2023,"publication_date":"2023-09-15","ids":{"openalex":"https://openalex.org/W4386763528","doi":"https://doi.org/10.1109/waspaa58266.2023.10248164"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa58266.2023.10248164","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/waspaa58266.2023.10248164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5036282544","display_name":"Wo Jae Lee","orcid":"https://orcid.org/0000-0002-2465-6296"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wo Jae Lee","raw_affiliation_strings":["Amazon Music"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Music","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041981312","display_name":"Emanuele Coviello","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emanuele Coviello","raw_affiliation_strings":["Amazon Music"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Music","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"1","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":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":0.9983000159263611,"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":0.9972000122070312,"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/singing","display_name":"Singing","score":0.7738249897956848},{"id":"https://openalex.org/keywords/instrumental-music","display_name":"Instrumental music","score":0.7054216861724854},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6639639139175415},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5984652638435364},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5462661385536194},{"id":"https://openalex.org/keywords/track","display_name":"Track (disk drive)","score":0.5219451785087585},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4211388826370239},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3968198299407959},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.19442516565322876},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.18443503975868225},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.11827981472015381},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.09530666470527649},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.06173017621040344},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06023603677749634}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7738249897956848},{"id":"https://openalex.org/C2993931450","wikidata":"https://www.wikidata.org/wiki/Q639197","display_name":"Instrumental music","level":3,"score":0.7054216861724854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6639639139175415},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5984652638435364},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5462661385536194},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.5219451785087585},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4211388826370239},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3968198299407959},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.19442516565322876},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.18443503975868225},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.11827981472015381},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.09530666470527649},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06173017621040344},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06023603677749634},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa58266.2023.10248164","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/waspaa58266.2023.10248164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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":38,"referenced_works":["https://openalex.org/W188353524","https://openalex.org/W1583001605","https://openalex.org/W1686810756","https://openalex.org/W1999454387","https://openalex.org/W2032362923","https://openalex.org/W2097574082","https://openalex.org/W2099620947","https://openalex.org/W2100772705","https://openalex.org/W2115717467","https://openalex.org/W2127870748","https://openalex.org/W2130770109","https://openalex.org/W2194775991","https://openalex.org/W2406222150","https://openalex.org/W2513345070","https://openalex.org/W2767858146","https://openalex.org/W2798069802","https://openalex.org/W2972737975","https://openalex.org/W3037149862","https://openalex.org/W3096787185","https://openalex.org/W3160719641","https://openalex.org/W3160747466","https://openalex.org/W3167533889","https://openalex.org/W3194581063","https://openalex.org/W4205523283","https://openalex.org/W4287634931","https://openalex.org/W4297775537","https://openalex.org/W4298310324","https://openalex.org/W4394647634","https://openalex.org/W6637373629","https://openalex.org/W6674917984","https://openalex.org/W6678969435","https://openalex.org/W6737664043","https://openalex.org/W6745878906","https://openalex.org/W6766320909","https://openalex.org/W6768465061","https://openalex.org/W6784990816","https://openalex.org/W6791192960","https://openalex.org/W6799643743"],"related_works":["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/W2366077683","https://openalex.org/W1501596003","https://openalex.org/W2368036937"],"abstract_inverted_index":{"A":[0],"large":[1],"scale":[2],"music":[3,21,92],"catalog":[4],"contains":[5],"diverse":[6],"types":[7],"of":[8,59,87],"sound":[9],"recordings.":[10],"In":[11],"this":[12],"paper,":[13],"we":[14,44,66],"present":[15],"a":[16,33,36,40,50,63,72,95],"methodology":[17],"to":[18,55,76],"identify":[19],"instrumental":[20,79,91],"with":[22,49],"high":[23,26],"precision":[24],"and":[25,39,80],"recall.":[27],"Our":[28],"method":[29],"starts":[30],"by":[31],"separating":[32],"recording":[34],"into":[35],"vocals":[37,47],"track":[38,48,70],"background":[41,69],"track.":[42],"Then,":[43],"process":[45],"the":[46,57,68,85],"singing":[51,60],"voice":[52,61],"detection":[53,93],"model,":[54],"estimate":[56],"amount":[58],"in":[62],"song.":[64],"Finally,":[65],"analyze":[67],"using":[71],"neural":[73],"network":[74],"trained":[75],"classify":[77],"be-tween":[78],"non-instrumental":[81],"sounds.":[82],"We":[83],"demonstrate":[84],"effectiveness":[86],"our":[88],"approach":[89],"on":[90],"through":[94],"comparative":[96],"evaluation":[97],"against":[98],"several":[99],"state-of-the-art":[100],"models.":[101]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}