{"id":"https://openalex.org/W4408354298","doi":"https://doi.org/10.1109/icassp49660.2025.10890222","title":"S-KEY: Self-supervised Learning of Major and Minor Keys from Audio","display_name":"S-KEY: Self-supervised Learning of Major and Minor Keys from Audio","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354298","doi":"https://doi.org/10.1109/icassp49660.2025.10890222"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890222","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890222","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/A5099057809","display_name":"Yuexuan Kong","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yuexuan Kong","raw_affiliation_strings":["Deezer Research,Paris,France"],"affiliations":[{"raw_affiliation_string":"Deezer Research,Paris,France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062693009","display_name":"Gabriel Meseguer-Brocal","orcid":"https://orcid.org/0000-0002-5232-8628"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gabriel Meseguer-Brocal","raw_affiliation_strings":["Deezer Research,Paris,France"],"affiliations":[{"raw_affiliation_string":"Deezer Research,Paris,France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027789239","display_name":"Vincent Lostanlen","orcid":"https://orcid.org/0000-0003-0580-1651"},"institutions":[{"id":"https://openalex.org/I100445878","display_name":"\u00c9cole Centrale de Nantes","ror":"https://ror.org/03nh7d505","country_code":"FR","type":"education","lineage":["https://openalex.org/I100445878","https://openalex.org/I97188460"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210117005","display_name":"Laboratoire des Sciences du Num\u00e9rique de Nantes","ror":"https://ror.org/02snf8m58","country_code":"FR","type":"facility","lineage":["https://openalex.org/I100445878","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I4210117005","https://openalex.org/I4210124215","https://openalex.org/I4210127572","https://openalex.org/I4210139971","https://openalex.org/I97188460","https://openalex.org/I97188460"]},{"id":"https://openalex.org/I97188460","display_name":"Nantes Universit\u00e9","ror":"https://ror.org/03gnr7b55","country_code":"FR","type":"education","lineage":["https://openalex.org/I97188460"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Vincent Lostanlen","raw_affiliation_strings":["Nantes Université,Centrale Nantes, CNRS, LS2N, UMR 6004,Nantes,France,F-44000"],"affiliations":[{"raw_affiliation_string":"Nantes Université,Centrale Nantes, CNRS, LS2N, UMR 6004,Nantes,France,F-44000","institution_ids":["https://openalex.org/I97188460","https://openalex.org/I100445878","https://openalex.org/I4210117005","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029522748","display_name":"Mathieu Lagrange","orcid":"https://orcid.org/0000-0002-1253-4427"},"institutions":[{"id":"https://openalex.org/I100445878","display_name":"\u00c9cole Centrale de Nantes","ror":"https://ror.org/03nh7d505","country_code":"FR","type":"education","lineage":["https://openalex.org/I100445878","https://openalex.org/I97188460"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210117005","display_name":"Laboratoire des Sciences du Num\u00e9rique de Nantes","ror":"https://ror.org/02snf8m58","country_code":"FR","type":"facility","lineage":["https://openalex.org/I100445878","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I4210117005","https://openalex.org/I4210124215","https://openalex.org/I4210127572","https://openalex.org/I4210139971","https://openalex.org/I97188460","https://openalex.org/I97188460"]},{"id":"https://openalex.org/I97188460","display_name":"Nantes Universit\u00e9","ror":"https://ror.org/03gnr7b55","country_code":"FR","type":"education","lineage":["https://openalex.org/I97188460"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mathieu Lagrange","raw_affiliation_strings":["Nantes Université,Centrale Nantes, CNRS, LS2N, UMR 6004,Nantes,France,F-44000"],"affiliations":[{"raw_affiliation_string":"Nantes Université,Centrale Nantes, CNRS, LS2N, UMR 6004,Nantes,France,F-44000","institution_ids":["https://openalex.org/I97188460","https://openalex.org/I100445878","https://openalex.org/I4210117005","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004879177","display_name":"Romain Hennequin","orcid":"https://orcid.org/0000-0001-8158-5562"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Romain Hennequin","raw_affiliation_strings":["Deezer Research,Paris,France"],"affiliations":[{"raw_affiliation_string":"Deezer Research,Paris,France","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5099057809"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7729,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.88371377,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9923999905586243,"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/computer-science","display_name":"Computer science","score":0.722957968711853},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6408676505088806},{"id":"https://openalex.org/keywords/minor","display_name":"Minor (academic)","score":0.4652695655822754},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4313172698020935},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.357417494058609},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.2203873097896576}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.722957968711853},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6408676505088806},{"id":"https://openalex.org/C2779760435","wikidata":"https://www.wikidata.org/wiki/Q5396169","display_name":"Minor (academic)","level":2,"score":0.4652695655822754},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4313172698020935},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.357417494058609},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2203873097896576},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890222","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890222","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":26,"referenced_works":["https://openalex.org/W1819763199","https://openalex.org/W2024595034","https://openalex.org/W2045135321","https://openalex.org/W2405656250","https://openalex.org/W3011176162","https://openalex.org/W3016115629","https://openalex.org/W3162528130","https://openalex.org/W3201143670","https://openalex.org/W4248171932","https://openalex.org/W4280498166","https://openalex.org/W4300957348","https://openalex.org/W4311137818","https://openalex.org/W4391822973","https://openalex.org/W4392904629","https://openalex.org/W4392931767","https://openalex.org/W4396877837","https://openalex.org/W6714030504","https://openalex.org/W6753689128","https://openalex.org/W6763354517","https://openalex.org/W6785932716","https://openalex.org/W6791537541","https://openalex.org/W6843552097","https://openalex.org/W6845137767","https://openalex.org/W6853393314","https://openalex.org/W6856125517","https://openalex.org/W6870742060"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2467936747","https://openalex.org/W2368619281","https://openalex.org/W2377143628","https://openalex.org/W2355995962","https://openalex.org/W2392462513","https://openalex.org/W2362718971","https://openalex.org/W2368173763"],"abstract_inverted_index":{"STONE,":[0,57],"the":[1,29,70,74,91,104,115],"current":[2],"method":[3],"in":[4,10,76,121],"self-supervised":[5,40,119],"learning":[6,34,41,120],"for":[7],"tonality":[8,77],"estimation":[9,78],"music":[11,122],"signals,":[12],"cannot":[13],"distinguish":[14],"relative":[15],"keys,":[16],"such":[17],"as":[18,63,95],"C":[19],"major":[20,43],"versus":[21],"A":[22],"minor.":[23],"In":[24],"this":[25,100],"article,":[26],"we":[27],"extend":[28],"neural":[30],"network":[31],"architecture":[32],"and":[33,44,81,89,102],"objective":[35],"of":[36,42,66,73,107,117],"STONE":[37],"to":[38,56,109],"perform":[39],"minor":[45],"keys":[46],"(S-KEY).":[47],"Our":[48],"main":[49],"contribution":[50],"is":[51],"an":[52],"auxiliary":[53],"pretext":[54],"task":[55],"formulated":[58],"using":[59],"transposition-invariant":[60],"chroma":[61],"features":[62],"a":[64,110],"source":[65],"pseudo-labels.":[67],"S-KEY":[68,108],"matches":[69],"supervised":[71],"state":[72],"art":[75],"on":[79],"FMAKv2":[80],"GTZAN":[82],"datasets":[83],"while":[84],"requiring":[85],"no":[86],"human":[87],"annotation":[88],"having":[90],"same":[92],"parameter":[93],"budget":[94],"STONE.":[96],"We":[97],"build":[98],"upon":[99],"result":[101],"expand":[103],"training":[105],"set":[106],"million":[111],"songs,":[112],"thus":[113],"showing":[114],"potential":[116],"large-scale":[118],"information":[123],"retrieval.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}