{"id":"https://openalex.org/W3200104365","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533328","title":"Audio DistilBERT: A Distilled Audio BERT for Speech Representation Learning","display_name":"Audio DistilBERT: A Distilled Audio BERT for Speech Representation Learning","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3200104365","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533328","mag":"3200104365"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533328","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100616400","display_name":"Fan Yu","orcid":"https://orcid.org/0000-0002-0576-7396"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Yu","raw_affiliation_strings":["Xi'an Jiaotong University, School of Computer Science & Technology,Xi'an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, School of Computer Science & Technology,Xi'an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101955304","display_name":"Jiawei Guo","orcid":"https://orcid.org/0000-0002-1787-1780"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Guo","raw_affiliation_strings":["Xi'an Jiaotong University, School of Software Engineering,Xi'an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, School of Software Engineering,Xi'an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050052141","display_name":"Wei Xi","orcid":"https://orcid.org/0000-0001-9348-2982"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xi","raw_affiliation_strings":["Xi'an Jiaotong University, School of Computer Science & Technology,Xi'an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, School of Computer Science & Technology,Xi'an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100634648","display_name":"Zhao Yang","orcid":"https://orcid.org/0000-0001-7681-1473"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Yang","raw_affiliation_strings":["Xi'an Jiaotong University, School of Computer Science & Technology,Xi'an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, School of Computer Science & Technology,Xi'an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101966096","display_name":"Rui Jiang","orcid":"https://orcid.org/0000-0001-5007-5746"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Jiang","raw_affiliation_strings":["Xi'an Jiaotong University, School of Computer Science & Technology,Xi'an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, School of Computer Science & Technology,Xi'an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100460186","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0002-5884-2169"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Xi'an Jiaotong University, School of Computer Science & Technology,Xi'an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, School of Computer Science & Technology,Xi'an,China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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":0.9986000061035156,"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":0.8253986239433289},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.744093656539917},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5033475756645203},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5001649856567383},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4996979236602783},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4734598994255066},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.45799264311790466},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39420849084854126},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3313751816749573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8253986239433289},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.744093656539917},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5033475756645203},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5001649856567383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4996979236602783},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4734598994255066},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.45799264311790466},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39420849084854126},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3313751816749573},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533328","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5823314271","display_name":null,"funder_award_id":"2018AAA0100500","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7308585218","display_name":null,"funder_award_id":"61832008,61772413","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1614298861","https://openalex.org/W1690739335","https://openalex.org/W1821462560","https://openalex.org/W2561238782","https://openalex.org/W2842511635","https://openalex.org/W2896457183","https://openalex.org/W2936774411","https://openalex.org/W2947454875","https://openalex.org/W2963140444","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2964118293","https://openalex.org/W2965373594","https://openalex.org/W2970454332","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2978017171","https://openalex.org/W2979476256","https://openalex.org/W2981991061","https://openalex.org/W2982223350","https://openalex.org/W2996383576","https://openalex.org/W2997006708","https://openalex.org/W2997666887","https://openalex.org/W3003875258","https://openalex.org/W3015213852","https://openalex.org/W3015356564","https://openalex.org/W3025035610","https://openalex.org/W3034457371","https://openalex.org/W3034560159","https://openalex.org/W3035030897","https://openalex.org/W3035365026","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3099782249","https://openalex.org/W3105966348","https://openalex.org/W3148040514","https://openalex.org/W4288348042","https://openalex.org/W4297808394","https://openalex.org/W4385245566","https://openalex.org/W6631362777","https://openalex.org/W6636510571","https://openalex.org/W6637551013","https://openalex.org/W6638523607","https://openalex.org/W6730179637","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6768086466","https://openalex.org/W6768851824","https://openalex.org/W6769196770","https://openalex.org/W6769238691","https://openalex.org/W6773206665","https://openalex.org/W6776076330","https://openalex.org/W6780218876","https://openalex.org/W6840487619"],"related_works":["https://openalex.org/W587737","https://openalex.org/W14551761","https://openalex.org/W11805017","https://openalex.org/W10360438","https://openalex.org/W10427218","https://openalex.org/W9205999","https://openalex.org/W505292","https://openalex.org/W4936768","https://openalex.org/W8319094","https://openalex.org/W10994108"],"abstract_inverted_index":{"Self-supervised":[0],"speech":[1,53],"representation":[2,54],"learning":[3,55],"has":[4],"been":[5],"considered":[6],"as":[7],"an":[8],"outstanding":[9],"manner":[10],"to":[11,29,147],"improve":[12],"the":[13,33,37,40,101,110,148,154,159],"performance":[14,84,108,145],"of":[15,39,109],"downstream":[16,97],"tasks.":[17],"However,":[18],"those":[19],"models":[20],"are":[21],"often":[22],"too":[23],"cumbersome,":[24],"which":[25,71],"sets":[26],"a":[27,50,62,126],"barrier":[28],"deploy":[30],"them":[31],"on":[32],"edge":[34],"and":[35,74,88,119,134,161],"improves":[36],"threshold":[38],"pre-training":[41],"process.":[42],"In":[43,125],"this":[44],"paper,":[45],"we":[46,152],"propose":[47],"Audio":[48],"DistilBERT,":[49],"distilled":[51],"BERT-style":[52],"method.":[56],"It":[57],"learns":[58],"dark":[59],"knowledge":[60,155],"from":[61],"larger":[63],"teacher":[64,160],"model":[65,112,117,138],"through":[66],"one":[67],"new":[68],"designed":[69],"loss":[70],"combines":[72],"soft":[73],"hard":[75],"targets.":[76],"By":[77],"doing":[78],"this,":[79],"it":[80],"can":[81,104],"achieve":[82],"competitive":[83],"with":[85,113,129],"fewer":[86],"parameters":[87],"faster":[89,122],"inference":[90,123],"time.":[91],"The":[92],"experimental":[93],"results":[94],"among":[95],"two":[96],"tasks":[98],"show":[99],"that":[100],"proposed":[102],"method":[103],"retain":[105],"above":[106],"98%":[107],"large":[111,149],"about":[114],"1.8\u00d7":[115],"smaller":[116],"size":[118],"over":[120],"1.6\u00d7":[121],"speed.":[124],"low-resource":[127],"environment":[128],"very":[130],"few":[131],"labeled":[132],"data":[133],"pretraining":[135],"steps,":[136],"our":[137],"also":[139],"exhibits":[140],"similar":[141],"or":[142],"even":[143],"better":[144],"compared":[146],"model.":[150,163],"Furthermore,":[151],"explore":[153],"transfer":[156],"competence":[157],"between":[158],"student":[162]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}