{"id":"https://openalex.org/W4401608950","doi":"https://doi.org/10.1109/icasspw62465.2024.10626360","title":"Investigating Design Choices in Joint-Embedding Predictive Architectures for General Audio Representation Learning","display_name":"Investigating Design Choices in Joint-Embedding Predictive Architectures for General Audio Representation Learning","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4401608950","doi":"https://doi.org/10.1109/icasspw62465.2024.10626360"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10626360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10626360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092829399","display_name":"Alain Riou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Alain Riou","raw_affiliation_strings":["Institut Polytechnique de Paris,LTCI, Télécom-Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, Télécom-Paris,France","institution_ids":["https://openalex.org/I4210165912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113914858","display_name":"Stefan Lattner","orcid":null},"institutions":[{"id":"https://openalex.org/I4210131385","display_name":"Sony (France)","ror":"https://ror.org/03cr99w51","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210131385","https://openalex.org/I4210143797"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Stefan Lattner","raw_affiliation_strings":["Sony Computer Science Laboratories,Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Computer Science Laboratories,Paris,France","institution_ids":["https://openalex.org/I4210131385"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051522702","display_name":"Ga\u00ebtan Hadjeres","orcid":"https://orcid.org/0000-0003-1462-6103"},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ga\u00ebtan Hadjeres","raw_affiliation_strings":["Sony AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063097936","display_name":"Geoffroy Peeters","orcid":"https://orcid.org/0000-0001-5255-3019"},"institutions":[{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Geoffroy Peeters","raw_affiliation_strings":["Institut Polytechnique de Paris,LTCI, Télécom-Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, Télécom-Paris,France","institution_ids":["https://openalex.org/I4210165912"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3057,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.51285177,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"680","last_page":"684"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.993399977684021,"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":0.993399977684021,"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":0.9678000211715698,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9496999979019165,"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/computer-science","display_name":"Computer science","score":0.7797091007232666},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7489107847213745},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6479089260101318},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5949805974960327},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44516465067863464},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4171917140483856},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4108749330043793},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39108750224113464},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38019832968711853},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37777960300445557},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3416200578212738},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07922032475471497}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7797091007232666},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7489107847213745},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6479089260101318},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5949805974960327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44516465067863464},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4171917140483856},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4108749330043793},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39108750224113464},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38019832968711853},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37777960300445557},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3416200578212738},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07922032475471497},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10626360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10626360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1835965142","https://openalex.org/W2030931454","https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2138621090","https://openalex.org/W2593116425","https://openalex.org/W2726515241","https://openalex.org/W2797583228","https://openalex.org/W2842511635","https://openalex.org/W3036601975","https://openalex.org/W3159239022","https://openalex.org/W3159481202","https://openalex.org/W3162391496","https://openalex.org/W3169212847","https://openalex.org/W3171007011","https://openalex.org/W4221145109","https://openalex.org/W4281758439","https://openalex.org/W4297808394","https://openalex.org/W4297841518","https://openalex.org/W4310873011","https://openalex.org/W4313156423","https://openalex.org/W4372341324","https://openalex.org/W4385245566","https://openalex.org/W4386076428","https://openalex.org/W6638699884","https://openalex.org/W6736723571","https://openalex.org/W6739901393","https://openalex.org/W6750665317","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6774314701","https://openalex.org/W6778102432","https://openalex.org/W6780218876","https://openalex.org/W6784333009","https://openalex.org/W6790850890","https://openalex.org/W6791742336","https://openalex.org/W6795754764","https://openalex.org/W6810007534","https://openalex.org/W6810510949","https://openalex.org/W6838322825"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W2849310602","https://openalex.org/W3006008237","https://openalex.org/W2419146053","https://openalex.org/W4388890789","https://openalex.org/W2088247287","https://openalex.org/W2963903416","https://openalex.org/W1996130883"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,13,43,48,52,93,109,122],"problem":[4],"of":[5,15,25,92],"self-supervised":[6],"general-purpose":[7],"audio":[8,75],"representation":[9],"learning.":[10],"We":[11,86],"explore":[12],"use":[14],"Joint-Embedding":[16],"Predictive":[17],"Architectures":[18],"(JEPA)":[19],"for":[20,39],"this":[21,60],"task,":[22],"which":[23,90],"consists":[24],"splitting":[26],"an":[27],"input":[28,94],"mel-spectrogram":[29],"into":[30],"two":[31,137],"parts":[32],"(context":[33],"and":[34,41,62,82,102],"target),":[35],"computing":[36],"neural":[37,44],"representations":[38,50],"each,":[40],"training":[42],"network":[45],"to":[46,126],"predict":[47],"target":[49,101],"from":[51],"context":[53,99],"representations.We":[54],"investigate":[55],"several":[56],"design":[57,119],"choices":[58,120],"within":[59],"framework":[61],"study":[63],"their":[64],"influence":[65],"through":[66],"extensive":[67],"experiments":[68],"by":[69],"evaluating":[70],"our":[71],"models":[72],"on":[73,89,129],"various":[74],"classification":[76],"benchmarks,":[77],"including":[78],"environmental":[79],"sounds,":[80],"speech":[81],"music":[83],"downstream":[84],"tasks.":[85],"focus":[87],"notably":[88],"part":[91],"data":[95],"is":[96],"used":[97],"as":[98],"or":[100],"show":[103],"experimentally":[104],"that":[105,116],"it":[106],"significantly":[107],"impacts":[108],"model\u2019s":[110],"quality.":[111],"In":[112],"particular,":[113],"we":[114],"notice":[115],"some":[117],"effective":[118],"in":[121],"image":[123],"domain":[124],"lead":[125],"poor":[127],"performance":[128],"audio,":[130],"thus":[131],"highlighting":[132],"major":[133],"differences":[134],"between":[135],"these":[136],"modalities.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}