{"id":"https://openalex.org/W4372260338","doi":"https://doi.org/10.1109/icassp49357.2023.10095041","title":"Audio Barlow Twins: Self-Supervised Audio Representation Learning","display_name":"Audio Barlow Twins: Self-Supervised Audio Representation Learning","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260338","doi":"https://doi.org/10.1109/icassp49357.2023.10095041"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095041","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5012745902","display_name":"Jonah Anton","orcid":"https://orcid.org/0000-0003-2424-8484"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jonah Anton","raw_affiliation_strings":["Imperial College,London,UK","Imperial College, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College,London,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Imperial College, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087769785","display_name":"Harry Coppock","orcid":"https://orcid.org/0000-0003-2404-8319"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Harry Coppock","raw_affiliation_strings":["Imperial College,London,UK","Imperial College, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College,London,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Imperial College, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005237446","display_name":"Pancham Shukla","orcid":"https://orcid.org/0000-0003-0707-8428"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pancham Shukla","raw_affiliation_strings":["Imperial College,London,UK","Imperial College, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College,London,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Imperial College, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["DE","GB"],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn W. Schuller","raw_affiliation_strings":["Imperial College,London,UK","EIHW, University of Augsburg, Germany","Imperial College, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College,London,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"EIHW, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]},{"raw_affiliation_string":"Imperial College, London, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5012745902"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":0.5737,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.62088627,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"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":1.0,"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":1.0,"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":0.9984999895095825,"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":0.9878000020980835,"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":0.7946910858154297},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5769030451774597},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5285467505455017},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5103527903556824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.489062637090683},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48280632495880127},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.46204468607902527},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.43987518548965454},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.42829132080078125},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37051475048065186},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.10456708073616028}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7946910858154297},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5769030451774597},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5285467505455017},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5103527903556824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.489062637090683},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48280632495880127},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.46204468607902527},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.43987518548965454},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.42829132080078125},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37051475048065186},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.10456708073616028},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095041","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W2593116425","https://openalex.org/W2896457183","https://openalex.org/W2962866891","https://openalex.org/W2965373594","https://openalex.org/W3005680577","https://openalex.org/W3035060554","https://openalex.org/W3036224891","https://openalex.org/W3036601975","https://openalex.org/W3038899388","https://openalex.org/W3093475354","https://openalex.org/W3093563057","https://openalex.org/W3134652006","https://openalex.org/W3137857706","https://openalex.org/W3145450063","https://openalex.org/W3158919880","https://openalex.org/W3159481202","https://openalex.org/W3169212847","https://openalex.org/W3171007011","https://openalex.org/W3175544090","https://openalex.org/W3201143670","https://openalex.org/W3206996142","https://openalex.org/W3213836217","https://openalex.org/W4221150524","https://openalex.org/W4283652729","https://openalex.org/W4285483774","https://openalex.org/W4310873011","https://openalex.org/W4311137818","https://openalex.org/W4312891522","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6774314701","https://openalex.org/W6779326418","https://openalex.org/W6779997284","https://openalex.org/W6780218876","https://openalex.org/W6780379688","https://openalex.org/W6784077883","https://openalex.org/W6786091203","https://openalex.org/W6786614245","https://openalex.org/W6790850890","https://openalex.org/W6791742336","https://openalex.org/W6793778002","https://openalex.org/W6797790494","https://openalex.org/W6803026232","https://openalex.org/W6804160461","https://openalex.org/W6809947431","https://openalex.org/W6810260272","https://openalex.org/W6838724896","https://openalex.org/W6840200333"],"related_works":["https://openalex.org/W614270737","https://openalex.org/W2207131324","https://openalex.org/W313445446","https://openalex.org/W1948589954","https://openalex.org/W2259508928","https://openalex.org/W2183768935","https://openalex.org/W2004123705","https://openalex.org/W197415996","https://openalex.org/W289407349","https://openalex.org/W2083892355"],"abstract_inverted_index":{"The":[0],"Barlow":[1,31,41],"Twins":[2,42],"self-supervised":[3,35,88],"learning":[4,12,38,89],"objective":[5],"requires":[6],"neither":[7],"negative":[8],"samples":[9],"or":[10,75],"asymmetric":[11],"updates,":[13],"achieving":[14,71],"results":[15,72],"on":[16,49,63,78],"a":[17,33,79],"par":[18,80],"with":[19],"the":[20,44,50,57,60,67,82],"current":[21,83],"state-of-the-art":[22,84],"within":[23],"Computer":[24],"Vision.":[25],"As":[26],"such,":[27],"we":[28],"present":[29],"Audio":[30],"Twins,":[32],"novel":[34],"audio":[36,45,52,92],"representation":[37,93],"approach,":[39],"adapting":[40],"to":[43,91],"domain.":[46],"We":[47],"pre-train":[48],"large-scale":[51],"dataset":[53],"AudioSet,":[54],"and":[55],"evaluate":[56],"quality":[58],"of":[59],"learnt":[61],"representations":[62],"18":[64],"tasks":[65],"from":[66],"HEAR":[68],"2021":[69],"Challenge,":[70],"which":[73],"outperform,":[74],"otherwise":[76],"are":[77],"with,":[81],"for":[85],"instance":[86],"discrimination":[87],"approaches":[90],"learning.":[94],"Code":[95],"at":[96],"https://github.com/jonahanton/SSL_audio.":[97]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-04T08:30:34.212998","created_date":"2025-10-10T00:00:00"}