{"id":"https://openalex.org/W3015949486","doi":"https://doi.org/10.1109/lsp.2020.2985586","title":"Pre-Training Audio Representations With Self-Supervision","display_name":"Pre-Training Audio Representations With Self-Supervision","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3015949486","doi":"https://doi.org/10.1109/lsp.2020.2985586","mag":"3015949486"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2020.2985586","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lsp.2020.2985586","pdf_url":"https://ieeexplore.ieee.org/ielx7/97/8966529/09060816.pdf","source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/97/8966529/09060816.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033341878","display_name":"Marco Tagliasacchi","orcid":"https://orcid.org/0000-0002-7682-6795"},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Marco Tagliasacchi","raw_affiliation_strings":["Google Research, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Google Research, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210100430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002559095","display_name":"Beat Gfeller","orcid":"https://orcid.org/0000-0002-1321-9015"},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Beat Gfeller","raw_affiliation_strings":["Google Research, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Google Research, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210100430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026916144","display_name":"F\u00e9lix de Chaumont Quitry","orcid":"https://orcid.org/0000-0003-4959-0016"},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Felix de Chaumont Quitry","raw_affiliation_strings":["Google Research, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Google Research, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210100430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011258273","display_name":"Dominik Roblek","orcid":"https://orcid.org/0000-0002-2155-450X"},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Dominik Roblek","raw_affiliation_strings":["Google Research, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Google Research, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210100430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5033341878"],"corresponding_institution_ids":["https://openalex.org/I4210100430"],"apc_list":null,"apc_paid":null,"fwci":5.9098,"has_fulltext":true,"cited_by_count":50,"citation_normalized_percentile":{"value":0.97156024,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"27","issue":null,"first_page":"600","last_page":"604"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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":0.9894999861717224,"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":0.8206588625907898},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7341800332069397},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.655979335308075},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6172170639038086},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5924071073532104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5415665507316589},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5182145237922668},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.46318650245666504},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4498353600502014},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.42972898483276367},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32817503809928894}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8206588625907898},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7341800332069397},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.655979335308075},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6172170639038086},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5924071073532104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5415665507316589},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5182145237922668},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.46318650245666504},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4498353600502014},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.42972898483276367},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32817503809928894},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2020.2985586","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lsp.2020.2985586","pdf_url":"https://ieeexplore.ieee.org/ielx7/97/8966529/09060816.pdf","source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/lsp.2020.2985586","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lsp.2020.2985586","pdf_url":"https://ieeexplore.ieee.org/ielx7/97/8966529/09060816.pdf","source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3015949486.pdf","grobid_xml":"https://content.openalex.org/works/W3015949486.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W343636949","https://openalex.org/W1494198834","https://openalex.org/W1614298861","https://openalex.org/W2086384421","https://openalex.org/W2144796873","https://openalex.org/W2219249508","https://openalex.org/W2321533354","https://openalex.org/W2326925005","https://openalex.org/W2487442924","https://openalex.org/W2550462002","https://openalex.org/W2561826558","https://openalex.org/W2575671312","https://openalex.org/W2593116425","https://openalex.org/W2606176153","https://openalex.org/W2767754137","https://openalex.org/W2774571176","https://openalex.org/W2785325870","https://openalex.org/W2797583228","https://openalex.org/W2799087757","https://openalex.org/W2804648901","https://openalex.org/W2804935296","https://openalex.org/W2883595988","https://openalex.org/W2890052321","https://openalex.org/W2916113431","https://openalex.org/W2939574508","https://openalex.org/W2950577311","https://openalex.org/W2962960500","https://openalex.org/W2962969419","https://openalex.org/W2963115079","https://openalex.org/W2963218389","https://openalex.org/W2963317665","https://openalex.org/W2963340922","https://openalex.org/W2963420272","https://openalex.org/W2963425185","https://openalex.org/W2963571336","https://openalex.org/W2964048159","https://openalex.org/W2964301993","https://openalex.org/W2973157397","https://openalex.org/W2997570773","https://openalex.org/W3008526508","https://openalex.org/W3104866538","https://openalex.org/W6636510571","https://openalex.org/W6688816777","https://openalex.org/W6736723571","https://openalex.org/W6746570019","https://openalex.org/W6747899497","https://openalex.org/W6750665317","https://openalex.org/W6751433836","https://openalex.org/W6754048563","https://openalex.org/W6774908330"],"related_works":["https://openalex.org/W4312887852","https://openalex.org/W2979740303","https://openalex.org/W2981877337","https://openalex.org/W3203938600","https://openalex.org/W4286910063","https://openalex.org/W2163707935","https://openalex.org/W83146503","https://openalex.org/W202723009","https://openalex.org/W2145955964","https://openalex.org/W2188612292"],"abstract_inverted_index":{"We":[0,50],"explore":[1],"self-supervision":[2,57],"as":[3],"a":[4,23,65,77],"way":[5],"to":[6,59,112],"learn":[7],"general":[8],"purpose":[9],"audio":[10,40,48],"representations.":[11],"Specifically,":[12],"we":[13],"propose":[14],"two":[15,38],"self-supervised":[16],"tasks:":[17],"Audio2Vec,":[18],"which":[19,33],"aims":[20],"at":[21,43],"reconstructing":[22],"spectrogram":[24],"slice":[25],"from":[26,45,117],"past":[27],"and":[28,31],"future":[29],"slices":[30],"TemporalGap,":[32],"estimates":[34],"the":[35,46,53,72,88],"distance":[36],"between":[37],"short":[39],"segments":[41],"extracted":[42],"random":[44],"same":[47],"clip.":[49],"evaluate":[51],"how":[52],"representations":[54,89,108],"learned":[55,90,97],"via":[56],"transfer":[58,93],"different":[60],"downstream":[61,82],"tasks,":[62],"either":[63],"training":[64,100],"task-specific":[66],"linear":[67],"classifier":[68],"on":[69,101,119],"top":[70],"of":[71],"pretrained":[73],"embeddings,":[74],"or":[75],"fine-tuning":[76,106],"model":[78],"end-to-end":[79],"for":[80],"each":[81,120],"task.":[83],"Our":[84],"results":[85],"show":[86],"that":[87],"with":[91],"Audio2Vec":[92,107],"better":[94],"than":[95],"those":[96],"by":[98,105],"fully-supervised":[99,114],"Audioset.":[102],"In":[103],"addition,":[104],"it":[109],"is":[110,125],"possible":[111],"outperform":[113],"models":[115],"trained":[116],"scratch":[118],"task,":[121],"when":[122],"limited":[123],"data":[124],"available,":[126],"thus":[127],"improving":[128],"label":[129],"efficiency.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":2}],"updated_date":"2026-02-27T16:54:17.756197","created_date":"2025-10-10T00:00:00"}