{"id":"https://openalex.org/W3083729638","doi":"https://doi.org/10.5281/zenodo.3887261","title":"Dataset used in COALA: Co-Aligned Autoencoders for Learning Semantically Enriched Audio Representations","display_name":"Dataset used in COALA: Co-Aligned Autoencoders for Learning Semantically Enriched Audio Representations","publication_year":2020,"publication_date":"2020-06-09","ids":{"openalex":"https://openalex.org/W3083729638","doi":"https://doi.org/10.5281/zenodo.3887261","mag":"3083729638"},"language":"en","primary_location":{"id":"pmh:oai:zenodo.org:3887261","is_oa":true,"landing_page_url":"https://zenodo.org/record/3887261","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/3887261","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066100176","display_name":"Xavier Favory","orcid":"https://orcid.org/0000-0001-6148-0018"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Favory, Xavier","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra"],"raw_orcid":"https://orcid.org/0000-0001-6148-0018","affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108358814","display_name":"Konstantinos Drossos","orcid":null},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Drossos, Konstantinos","raw_affiliation_strings":["Audio Research Group, Faculty of Information Technology and Communication Sciences, Tampere University"],"raw_orcid":"https://orcid.org/0000-0002-3605-7127","affiliations":[{"raw_affiliation_string":"Audio Research Group, Faculty of Information Technology and Communication Sciences, Tampere University","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049691461","display_name":"Tuomas Virtanen","orcid":"https://orcid.org/0000-0002-4604-9729"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Virtanen, Tuomas","raw_affiliation_strings":["Audio Research Group, Faculty of Information Technology and Communication Sciences, Tampere University"],"raw_orcid":"https://orcid.org/0000-0002-4604-9729","affiliations":[{"raw_affiliation_string":"Audio Research Group, Faculty of Information Technology and Communication Sciences, Tampere University","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006479715","display_name":"Xavier Serra","orcid":"https://orcid.org/0000-0003-1395-2345"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Serra, Xavier","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra"],"raw_orcid":"https://orcid.org/0000-0003-1395-2345","affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra","institution_ids":["https://openalex.org/I170486558"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":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":0.9843999743461609,"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":0.9843999743461609,"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":0.9322999715805054,"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":0.6093452572822571},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4140976071357727},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4062393605709076},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37892985343933105},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.322878897190094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6093452572822571},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4140976071357727},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4062393605709076},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37892985343933105},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.322878897190094}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:zenodo.org:3887261","is_oa":true,"landing_page_url":"https://zenodo.org/record/3887261","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"dataset"},{"id":"doi:10.5281/zenodo.3887261","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.3887261","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:3887261","is_oa":true,"landing_page_url":"https://zenodo.org/record/3887261","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W3204019825"],"abstract_inverted_index":{"This":[0,91],"dataset":[1,23,92,127],"consists":[2],"of":[3,50,120],"two":[4],"hdf5":[5],"files":[6],"that":[7,12],"contain":[8],"pre-computed":[9],"log-mel":[10],"spectrograms":[11],"have":[13],"been":[14],"used":[15,124],"to":[16,17],"train":[18],"audio":[19],"embedding":[20],"models.":[21],"The":[22,82],"is":[24,84,93],"split":[25],"into":[26],"a":[27,31,48],"training":[28],"set":[29,33],"and":[30,37,79,128],"validation":[32],"containing":[34],"respectively":[35],"170793":[36],"19103":[38],"spectrogram":[39],"patches":[40],"with":[41],"their":[42,130],"accompanying":[43],"multi-hot":[44],"encoded":[45],"tags":[46,52],"from":[47,95,97,110],"vocabulary":[49],"1000":[51],"provided":[53],"by":[54,72],"Freesound":[55,99],"users.":[56],"More":[57],"details":[58],"can":[59],"be":[60],"found":[61],"in":[62,125,133],"\"COALA:":[63],"Co-Aligned":[64],"Autoencoders":[65],"for":[66],"Learning":[67],"Semantically":[68],"Enriched":[69],"Audio":[70],"Representations\"":[71],"X.":[73,80],"Favory,":[74],"K.":[75],"Drossos,":[76],"T.":[77],"Virtanen,":[78],"Serra.":[81],"code":[83],"available":[85],"at":[86],"this":[87],"GitHub":[88],"repository.":[89],"License:":[90],"derived":[94],"content":[96],"the":[98,122,126,134],"collection.":[100],"All":[101],"sounds":[102,123],"are":[103],"released":[104],"under":[105],"Creative":[106],"Commons":[107],"(CC)":[108],"licenses":[109,132],"either":[111],"CC0,":[112],"CC-BY,":[113],"CC-S+,":[114],"or":[115],"CC-BY-NC.":[116],"We":[117],"attribute":[118],"authors":[119],"all":[121],"provide":[129],"corresponding":[131],"attributions.txt":[135],"file.":[136]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}
