{"id":"https://openalex.org/W7108737022","doi":"https://doi.org/10.5281/zenodo.17811559","title":"From Discord to Harmony: Decomposed Consonance-based Training for Improved Audio Chord Estimation","display_name":"From Discord to Harmony: Decomposed Consonance-based Training for Improved Audio Chord Estimation","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7108737022","doi":"https://doi.org/10.5281/zenodo.17811559"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.17811559","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811559","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":"ConferencePaper"},"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.17811559","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Andrea Poltronieri","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrea Poltronieri","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xavier Serra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xavier Serra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Mart\u00edn Rocamora","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mart\u00edn Rocamora","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.54151398,"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":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9804999828338623,"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":0.9804999828338623,"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":0.008799999952316284,"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":0.003599999938160181,"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/chord","display_name":"Chord (peer-to-peer)","score":0.9064000248908997},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4025999903678894},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.40149998664855957},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.335099995136261},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.3294999897480011},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.3111000061035156}],"concepts":[{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.9064000248908997},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6442999839782715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47909998893737793},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4311999976634979},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4025999903678894},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.40149998664855957},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3659999966621399},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.335099995136261},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.3294999897480011},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.274399995803833},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26429998874664307},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2583000063896179},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2572000026702881}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.17811559","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811559","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":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.5281/zenodo.17811559","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811559","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":"ConferencePaper"},"sustainable_development_goals":[{"score":0.6677221059799194,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Audio":[0],"Chord":[1],"Estimation":[2],"(ACE)":[3],"holds":[4],"a":[5,51,90,96,138],"pivotal":[6],"role":[7],"in":[8,33,46,84,103],"music":[9,24],"information":[10],"research,":[11],"having":[12],"garnered":[13],"attention":[14],"for":[15,23,99],"over":[16],"two":[17],"decades":[18],"due":[19],"to":[20,65,80,165],"its":[21],"relevance":[22],"transcription":[25],"and":[26,67,87,169],"analysis.":[27],"Despite":[28],"notable":[29],"advancements,":[30],"challenges":[31,55],"persist":[32],"the":[34,119,148,174],"task,":[35],"particularly":[36],"concerning":[37],"unique":[38],"characteristics":[39],"of":[40,126,176],"harmonic":[41],"content,":[42],"which":[43],"have":[44],"resulted":[45],"existing":[47],"systems'":[48],"performances":[49],"reaching":[50],"glass":[52],"ceiling.":[53],"These":[54],"include":[56],"annotator":[57],"subjectivity,":[58],"where":[59,73],"varying":[60],"interpretations":[61],"among":[62],"annotators":[63],"lead":[64],"inconsistencies,":[66],"class":[68,159],"imbalance":[69,160],"within":[70],"chord":[71,75,104,177],"datasets,":[72],"certain":[74],"classes":[76],"are":[77],"over-represented":[78],"compared":[79],"others,":[81],"posing":[82],"difficulties":[83],"model":[85,142,149,156],"training":[86,163],"evaluation.":[88],"As":[89],"first":[91],"contribution,":[92],"this":[93,180],"paper":[94],"presents":[95],"novel":[97,139],"methodology":[98],"assessing":[100],"inter-annotator":[101],"agreement":[102,130],"annotations,":[105],"using":[106],"metrics":[107,121],"that":[108,117,143],"extend":[109],"beyond":[110],"traditional":[111],"binary":[112],"measures.":[113],"Our":[114],"analysis":[115],"demonstrates":[116],"incorporating":[118],"distance":[120],"based":[122],"on":[123,133],"perceptual":[124],"concepts":[125,146],"consonance":[127,145],"significantly":[128],"enhances":[129],"scores.":[131],"Expanding":[132],"these":[134],"findings,":[135],"we":[136],"introduce":[137],"ACE":[140],"conformer-based":[141],"integrates":[144],"into":[147],"through":[150],"consonance-based":[151],"label":[152],"smoothing.":[153],"The":[154],"proposed":[155],"also":[157],"addresses":[158],"by":[161],"separately":[162],"models":[164],"detect":[166],"root,":[167],"bass,":[168],"all":[170],"note":[171],"activations,":[172],"enabling":[173],"reconstruction":[175],"labels":[178],"from":[179],"information.":[181]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-12-05T00:00:00"}