{"id":"https://openalex.org/W4297841518","doi":"https://doi.org/10.21437/interspeech.2022-10126","title":"ATST: Audio Representation Learning with Teacher-Student Transformer","display_name":"ATST: Audio Representation Learning with Teacher-Student Transformer","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841518","doi":"https://doi.org/10.21437/interspeech.2022-10126"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10126","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10126","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5100727621","display_name":"Xian Li","orcid":"https://orcid.org/0000-0001-8410-1586"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]},{"id":"https://openalex.org/I4210137766","display_name":"Institute for Advanced Study","ror":"https://ror.org/03xg85719","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210137766"]}],"countries":["CN","DE"],"is_corresponding":true,"raw_author_name":"Xian LI","raw_affiliation_strings":["Westlake University , Hangzhou, China","Westlake Institute for Advanced Study &"],"affiliations":[{"raw_affiliation_string":"Westlake University , Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]},{"raw_affiliation_string":"Westlake Institute for Advanced Study &","institution_ids":["https://openalex.org/I4210137766","https://openalex.org/I3133055985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100358313","display_name":"Xiaofei Li","orcid":"https://orcid.org/0000-0003-0393-9905"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]},{"id":"https://openalex.org/I4210137766","display_name":"Institute for Advanced Study","ror":"https://ror.org/03xg85719","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210137766"]}],"countries":["CN","DE"],"is_corresponding":false,"raw_author_name":"Xiaofei Li","raw_affiliation_strings":["Westlake Institute for Advanced Study &","Westlake University , Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Westlake Institute for Advanced Study &","institution_ids":["https://openalex.org/I4210137766","https://openalex.org/I3133055985"]},{"raw_affiliation_string":"Westlake University , Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100727621"],"corresponding_institution_ids":["https://openalex.org/I3133055985","https://openalex.org/I4210137766"],"apc_list":null,"apc_paid":null,"fwci":2.067,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.89735516,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4172","last_page":"4176"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.996999979019165,"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":0.996999979019165,"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":0.9923999905586243,"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":0.9817000031471252,"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/transformer","display_name":"Transformer","score":0.7607817053794861},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7347689867019653},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7313178181648254},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6228532195091248},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43731021881103516},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42773985862731934},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11348098516464233},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08955252170562744},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.07836350798606873}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7607817053794861},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7347689867019653},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7313178181648254},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6228532195091248},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43731021881103516},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42773985862731934},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11348098516464233},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08955252170562744},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.07836350798606873},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10126","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10126","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2038484192","https://openalex.org/W2593116425","https://openalex.org/W2606176153","https://openalex.org/W2726515241","https://openalex.org/W2797583228","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2982223350","https://openalex.org/W3006926732","https://openalex.org/W3015949486","https://openalex.org/W3035060554","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3093563057","https://openalex.org/W3094550259","https://openalex.org/W3137857706","https://openalex.org/W3159481202","https://openalex.org/W3169320628","https://openalex.org/W3196974791","https://openalex.org/W3201143670","https://openalex.org/W3205550549","https://openalex.org/W3206996142","https://openalex.org/W4287592659","https://openalex.org/W4297808394","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2275988210","https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4224009465","https://openalex.org/W2385621972","https://openalex.org/W4286629047","https://openalex.org/W4306321456","https://openalex.org/W4285260836","https://openalex.org/W4320830014","https://openalex.org/W4386566506"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1],"(SSL)":[2],"learns":[3],"knowledge":[4,16],"from":[5],"a":[6,18,22,48,62,78],"large":[7],"amount":[8],"of":[9,25,41,74,92,111],"unlabeled":[10],"data,":[11],"and":[12,46,99],"then":[13],"transfers":[14],"the":[15,39,71,90,100,104,112],"to":[17,87],"specific":[19],"problem":[20,40],"with":[21],"limited":[23],"number":[24],"labeled":[26],"data.":[27],"SSL":[28,52],"has":[29],"achieved":[30],"promising":[31],"results":[32,107],"in":[33],"various":[34],"domains.":[35],"This":[36],"work":[37],"addresses":[38],"segment-level":[42],"general":[43],"audio":[44],"SSL,":[45],"proposes":[47],"new":[49,79,105],"transformer-based":[50],"teacher-student":[51,65],"model,":[53],"named":[54],"ATST.":[55],"A":[56],"transformer":[57],"encoder":[58],"is":[59,85],"developed":[60],"on":[61,108],"recently":[63],"emerged":[64],"baseline":[66],"scheme,":[67],"which":[68],"largely":[69],"improves":[70],"modeling":[72],"capability":[73,91],"pre-training.":[75],"In":[76],"addition,":[77],"strategy":[80],"for":[81],"positive":[82],"pair":[83],"creation":[84],"designed":[86],"fully":[88],"leverage":[89],"transformer.":[93],"Extensive":[94],"experiments":[95],"have":[96],"been":[97],"conducted,":[98],"proposed":[101],"model":[102],"achieves":[103],"state-of-the-art":[106],"almost":[109],"all":[110],"downstream":[113],"tasks.":[114]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":3}],"updated_date":"2026-04-02T13:48:15.688549","created_date":"2025-10-10T00:00:00"}