{"id":"https://openalex.org/W6892466077","doi":"https://doi.org/10.5281/zenodo.10265414","title":"Efficient Supervised Training of Audio Transformers for Music Representation Learning","display_name":"Efficient Supervised Training of Audio Transformers for Music Representation Learning","publication_year":2023,"publication_date":"2023-11-04","ids":{"openalex":"https://openalex.org/W6892466077","doi":"https://doi.org/10.5281/zenodo.10265414"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.10265414","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265414","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.10265414","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Pablo Alonso-Jim\u00e9nez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pablo Alonso-Jim\u00e9nez","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":"Dmitry Bogdanov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dmitry Bogdanov","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":0.31635043,"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":0.9218000173568726,"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":0.9218000173568726,"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":0.028699999675154686,"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":0.011599999852478504,"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/transformer","display_name":"Transformer","score":0.6553000211715698},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6337000131607056},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6299999952316284},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5421000123023987},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.40549999475479126},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.3528999984264374},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.34279999136924744},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3249000012874603}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7914000153541565},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6553000211715698},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6337000131607056},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6299999952316284},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5421000123023987},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5217999815940857},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49300000071525574},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.412200003862381},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.40549999475479126},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3528999984264374},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.34279999136924744},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2874000072479248},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28119999170303345},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27160000801086426},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2630999982357025},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.10265414","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265414","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.10265414","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265414","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,37],"this":[1],"work,":[2],"we":[3,42],"address":[4],"music":[5,50,178],"representation":[6],"learning":[7],"using":[8,31,72,78,147],"convolution-free":[9],"transformers.":[10],"We":[11,60,102],"build":[12],"on":[13,27,56],"top":[14],"of":[15,54,64,86,142],"existing":[16,70],"spectrogram-based":[17],"audio":[18,75,108],"transformers":[19],"such":[20],"as":[21],"AST":[22],"and":[23,84,92,115,125,145,169],"train":[24],"our":[25,155],"models":[26,176],"a":[28],"supervised":[29],"task":[30],"patchout":[32,94,148],"training":[33,58,67,109,124],"similar":[34],"to":[35,39,97],"PaSST.":[36],"contrast":[38],"previous":[40],"works,":[41],"study":[43],"how":[44],"specific":[45],"design":[46],"decisions":[47],"affect":[48],"downstream":[49,90,126,134],"tagging":[51,179],"tasks":[52,135],"instead":[53],"focusing":[55],"the":[57,62,66,87,107,123,129,133,139,143,171],"task.":[59],"assess":[61],"impact":[63],"initializing":[65,106],"with":[68],"different":[69,82],"weights,":[71],"various":[73],"input":[74,117],"segment":[76],"lengths,":[77],"learned":[79],"representations":[80,131],"from":[81,110],"blocks":[83,141],"tokens":[85],"transformer":[88],"for":[89,122,132],"tasks,":[91,127],"applying":[93],"at":[95,149],"inference":[96,150],"speed":[98],"up":[99],"feature":[100],"extraction.":[101],"find":[103],"that":[104],"1)":[105],"ImageNet":[111],"or":[112],"AudioSet":[113],"weights":[114],"longer":[116],"segments":[118],"are":[119,136,166],"beneficial":[120],"both":[121],"2)":[128],"best":[130,172],"located":[137],"in":[138,177],"middle":[140],"transformer,":[144],"3)":[146],"allows":[151],"faster":[152],"processing":[153],"than":[154],"convolutional":[156],"baselines":[157],"while":[158],"maintaining":[159],"superior":[160],"performance.":[161],"The":[162],"resulting":[163],"models,":[164],"MAEST,":[165],"publicly":[167],"available":[168],"obtain":[170],"performance":[173],"among":[174],"open":[175],"tasks.":[180]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}