{"id":"https://openalex.org/W4408345573","doi":"https://doi.org/10.1109/icassp49660.2025.10888146","title":"COCOLA: Coherence-Oriented Contrastive Learning of Musical Audio Representations","display_name":"COCOLA: Coherence-Oriented Contrastive Learning of Musical Audio Representations","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345573","doi":"https://doi.org/10.1109/icassp49660.2025.10888146"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888146","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":true,"oa_status":"green","oa_url":"https://hdl.handle.net/10278/5113188","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5097358252","display_name":"Ruben Ciranni","orcid":null},"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":true,"raw_author_name":"Ruben Ciranni","raw_affiliation_strings":["Sapienza University of Rome,Italy"],"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome,Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032905625","display_name":"Giorgio Mariani","orcid":"https://orcid.org/0000-0002-8135-0330"},"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":"Giorgio Mariani","raw_affiliation_strings":["Sapienza University of Rome,Italy"],"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome,Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076690986","display_name":"Michele Mancusi","orcid":"https://orcid.org/0000-0003-1591-7076"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michele Mancusi","raw_affiliation_strings":["Sony Europe B.V.,Stuttgart,Germany"],"affiliations":[{"raw_affiliation_string":"Sony Europe B.V.,Stuttgart,Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069620223","display_name":"Emilian Postolache","orcid":"https://orcid.org/0000-0002-4785-5204"},"institutions":[{"id":"https://openalex.org/I149461666","display_name":"Ca' Foscari University of Venice","ror":"https://ror.org/04yzxz566","country_code":"IT","type":"education","lineage":["https://openalex.org/I149461666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Emilian Postolache","raw_affiliation_strings":["Ca&#x2019; Foscari University of Venice,DAIS,Italy"],"affiliations":[{"raw_affiliation_string":"Ca&#x2019; Foscari University of Venice,DAIS,Italy","institution_ids":["https://openalex.org/I149461666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006089763","display_name":"Giorgio Fabbro","orcid":"https://orcid.org/0000-0002-6302-9033"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Giorgio Fabbro","raw_affiliation_strings":["Sony Europe B.V.,Stuttgart,Germany"],"affiliations":[{"raw_affiliation_string":"Sony Europe B.V.,Stuttgart,Germany","institution_ids":[]}]},{"author_position":"middle","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\u00e0","raw_affiliation_strings":["Sapienza University of Rome,Italy"],"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome,Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085428440","display_name":"Luca Cosmo","orcid":"https://orcid.org/0000-0001-7729-4666"},"institutions":[{"id":"https://openalex.org/I149461666","display_name":"Ca' Foscari University of Venice","ror":"https://ror.org/04yzxz566","country_code":"IT","type":"education","lineage":["https://openalex.org/I149461666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Cosmo","raw_affiliation_strings":["Ca&#x2019; Foscari University of Venice,DAIS,Italy"],"affiliations":[{"raw_affiliation_string":"Ca&#x2019; Foscari University of Venice,DAIS,Italy","institution_ids":["https://openalex.org/I149461666"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5097358252"],"corresponding_institution_ids":["https://openalex.org/I861853513"],"apc_list":null,"apc_paid":null,"fwci":8.9479,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.97962735,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9979000091552734,"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":0.9936000108718872,"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/computer-science","display_name":"Computer science","score":0.7360137104988098},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.7134742736816406},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.5556280612945557},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4618235230445862},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.357479453086853},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.08035203814506531},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.058229535818099976},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05715674161911011}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7360137104988098},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.7134742736816406},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.5556280612945557},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4618235230445862},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.357479453086853},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.08035203814506531},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.058229535818099976},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05715674161911011},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888146","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"},{"id":"pmh:oai:iris.unive.it:10278/5113188","is_oa":true,"landing_page_url":"https://hdl.handle.net/10278/5113188","pdf_url":null,"source":{"id":"https://openalex.org/S4306402336","display_name":"ARCA (Universit\u00e0 Ca' Foscari Venezia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149461666","host_organization_name":"Ca' Foscari University of Venice","host_organization_lineage":["https://openalex.org/I149461666"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:iris.unive.it:10278/5113188","is_oa":true,"landing_page_url":"https://hdl.handle.net/10278/5113188","pdf_url":null,"source":{"id":"https://openalex.org/S4306402336","display_name":"ARCA (Universit\u00e0 Ca' Foscari Venezia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149461666","host_organization_name":"Ca' Foscari University of Venice","host_organization_lineage":["https://openalex.org/I149461666"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W2157364932","https://openalex.org/W2767754137","https://openalex.org/W2972478942","https://openalex.org/W2973157397","https://openalex.org/W2998490864","https://openalex.org/W3088329082","https://openalex.org/W3145867403","https://openalex.org/W3162391496","https://openalex.org/W4224297089","https://openalex.org/W4225314222","https://openalex.org/W4307323391","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4382203562","https://openalex.org/W4390872297","https://openalex.org/W4390873054","https://openalex.org/W4392902957","https://openalex.org/W4392904047","https://openalex.org/W4392904237","https://openalex.org/W4401023775","https://openalex.org/W4408345930","https://openalex.org/W6633727632","https://openalex.org/W6762718338","https://openalex.org/W6763945542","https://openalex.org/W6769627184","https://openalex.org/W6773772901","https://openalex.org/W6774212381","https://openalex.org/W6774314701","https://openalex.org/W6779191341","https://openalex.org/W6779823529","https://openalex.org/W6781319653","https://openalex.org/W6786375611","https://openalex.org/W6791537541","https://openalex.org/W6840200333","https://openalex.org/W6843026064","https://openalex.org/W6844035133","https://openalex.org/W6844194202","https://openalex.org/W6846591948","https://openalex.org/W6846753064","https://openalex.org/W6848578254","https://openalex.org/W6848854281","https://openalex.org/W6849517043","https://openalex.org/W6849887002","https://openalex.org/W6851290578","https://openalex.org/W6854494257","https://openalex.org/W6855434424","https://openalex.org/W6861353174","https://openalex.org/W6868771744","https://openalex.org/W6869810883","https://openalex.org/W6876063710"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"We":[0,84],"present":[1],"COCOLA":[2,47],"(Coherence-Oriented":[3],"Contrastive":[4],"Learning":[5],"for":[6,12,55],"Audio),":[7],"a":[8],"contrastive":[9],"learning":[10],"method":[11,26],"musical":[13],"audio":[14],"representations":[15],"that":[16],"captures":[17],"the":[18,29,32,78,86],"harmonic":[19],"and":[20,38,99],"rhythmic":[21],"coherence":[22],"between":[23],"samples.":[24],"Our":[25],"operates":[27],"at":[28],"level":[30],"of":[31,52,80],"individual":[33],"stems":[34,95],"composing":[35],"music":[36,56,73],"tracks":[37],"can":[39],"input":[40],"features":[41],"obtained":[42],"via":[43],"Harmonic-Percussive":[44],"Separation":[45],"(HPS).":[46],"allows":[48],"an":[49],"objective":[50],"evaluation":[51],"generative":[53],"models":[54],"accompaniment":[57,74],"generation,":[58],"which":[59],"are":[60],"difficult":[61],"to":[62],"benchmark":[63],"with":[64],"established":[65],"metrics.":[66],"In":[67],"this":[68],"regard,":[69],"we":[70],"evaluate":[71],"recent":[72],"generation":[75],"models,":[76],"demonstrating":[77],"effectiveness":[79],"our":[81],"proposed":[82],"method.":[83],"release":[85],"model":[87],"checkpoints":[88],"trained":[89],"on":[90],"public":[91],"datasets":[92],"containing":[93],"separate":[94],"(MUSDB18-HQ,":[96],"MoisesDB,":[97],"Slakh2100,":[98],"CocoChorales).":[100]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}
