{"id":"https://openalex.org/W6893158533","doi":"https://doi.org/10.5281/zenodo.14877489","title":"STONE: Self-Supervised Tonality Estimator","display_name":"STONE: Self-Supervised Tonality Estimator","publication_year":2024,"publication_date":"2024-11-10","ids":{"openalex":"https://openalex.org/W6893158533","doi":"https://doi.org/10.5281/zenodo.14877489"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14877489","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877489","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.14877489","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yuexuan Kong","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yuexuan Kong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Vincent Lostanlen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vincent Lostanlen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Gabriel Meseguer-Brocal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gabriel Meseguer-Brocal","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Stella Wong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stella Wong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Mathieu Lagrange","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mathieu Lagrange","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Romain Hennequin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Romain Hennequin","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37445123,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9635000228881836,"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":0.9635000228881836,"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":0.01860000006854534,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.005499999970197678,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/tonality","display_name":"Tonality","score":0.9745000004768372},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.7024000287055969},{"id":"https://openalex.org/keywords/octave","display_name":"Octave (electronics)","score":0.6966999769210815},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6704999804496765},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5702999830245972},{"id":"https://openalex.org/keywords/major-and-minor","display_name":"Major and minor","score":0.44600000977516174},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4099999964237213},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.40369999408721924}],"concepts":[{"id":"https://openalex.org/C2776275044","wikidata":"https://www.wikidata.org/wiki/Q192822","display_name":"Tonality","level":3,"score":0.9745000004768372},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.7024000287055969},{"id":"https://openalex.org/C85841341","wikidata":"https://www.wikidata.org/wiki/Q1135984","display_name":"Octave (electronics)","level":2,"score":0.6966999769210815},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6704999804496765},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6011999845504761},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5911999940872192},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5702999830245972},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5375999808311462},{"id":"https://openalex.org/C180010258","wikidata":"https://www.wikidata.org/wiki/Q1439151","display_name":"Major and minor","level":2,"score":0.44600000977516174},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4099999964237213},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.40369999408721924},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3799999952316284},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34700000286102295},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3068000078201294},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2973000109195709},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2777999937534332},{"id":"https://openalex.org/C2779760435","wikidata":"https://www.wikidata.org/wiki/Q5396169","display_name":"Minor (academic)","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C2779696439","wikidata":"https://www.wikidata.org/wiki/Q7512811","display_name":"Signature (topology)","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2623000144958496},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2614000141620636},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C2983311337","wikidata":"https://www.wikidata.org/wiki/Q34379","display_name":"Musical instrument","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14877489","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877489","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":""}],"best_oa_location":{"id":"doi:10.5281/zenodo.14877489","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877489","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Although":[0],"deep":[1],"neural":[2],"networks":[3],"can":[4],"estimate":[5],"the":[6,25,69,81,128,176],"key":[7,99,130],"of":[8,49,83,113,135,157,165,179],"a":[9,15,37,44,110,154],"musical":[10,66,160],"piece,":[11],"their":[12],"supervision":[13,118,136,183],"incurs":[14],"massive":[16],"annotation":[17,164],"effort.":[18],"Against":[19],"this":[20,89,103],"shortcoming,":[21],"we":[22,54,105],"present":[23],"STONE,":[24,33],"first":[26],"self-supervised":[27,90],"tonality":[28,142],"estimator.":[29],"The":[30],"architecture":[31],"behind":[32],"named":[34],"ChromaNet,":[35],"is":[36],"convnet":[38],"with":[39,97,162,181,187],"octave":[40],"equivalence":[41],"which":[42],"outputs":[43],"\"key":[45],"signature":[46],"profile\"":[47],"(KSP)":[48],"12":[50],"structured":[51,111],"logits.":[52],"First,":[53],"train":[55],"ChromaNet":[56],"to":[57,95,108,121],"regress":[58],"artificial":[59],"pitch":[60],"transpositions":[61],"between":[62],"any":[63],"two":[64],"unlabeled":[65],"excerpts":[67],"from":[68],"same":[70,129],"audio":[71],"track,":[72],"as":[73,75,120],"measured":[74],"cross-power":[76],"spectral":[77],"density":[78],"(CPSD)":[79],"within":[80],"circle":[82],"fifths":[84],"(CoF).":[85],"We":[86,148,171],"observe":[87],"that":[88,173],"pretext":[91],"task":[92],"leads":[93],"KSP":[94,112],"correlate":[96],"tonal":[98],"signature.":[100,131],"Based":[101],"on":[102,152],"observation,":[104],"extend":[106],"STONE":[107],"output":[109],"24":[114,166],"logits,":[115],"and":[116,139,146,168,184],"introduce":[117],"so":[119],"disambiguate":[122],"major":[123,167],"versus":[124],"minor":[125,169],"keys":[126],"sharing":[127],"Applying":[132],"different":[133],"amounts":[134],"yields":[137],"semi-supervised":[138],"fully":[140],"supervised":[141],"estimators:":[143],"i.e.,":[144],"Semi-TONEs":[145],"Sup-TONEs.":[147],"evaluate":[149],"these":[150],"estimators":[151],"FMAK,":[153],"new":[155],"dataset":[156],"5489":[158],"real-world":[159],"recordings":[161],"expert":[163],"keys.":[170],"find":[172],"Semi-TONE":[174],"matches":[175],"classification":[177],"accuracy":[178],"Sup-TONE":[180],"reduced":[182],"outperforms":[185],"it":[186],"equal":[188],"supervision.":[189]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}