{"id":"https://openalex.org/W3148040514","doi":"https://doi.org/10.1109/slt48900.2021.9383575","title":"Audio Albert: A Lite Bert for Self-Supervised Learning of Audio Representation","display_name":"Audio Albert: A Lite Bert for Self-Supervised Learning of Audio Representation","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3148040514","doi":"https://doi.org/10.1109/slt48900.2021.9383575","mag":"3148040514"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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/A5069156649","display_name":"Po-Han Chi","orcid":"https://orcid.org/0000-0001-8183-3781"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Po-Han Chi","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072966779","display_name":"Pei-Hung Chung","orcid":"https://orcid.org/0000-0002-8506-6791"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Pei-Hung Chung","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101804850","display_name":"Tsung-Han Wu","orcid":"https://orcid.org/0000-0002-5071-0583"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tsung-Han Wu","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044430316","display_name":"Chun-Cheng Hsieh","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chun-Cheng Hsieh","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020114965","display_name":"Yen\u2010Hao Chen","orcid":"https://orcid.org/0000-0002-5622-5490"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yen-Hao Chen","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029566548","display_name":"Shang-Wen Li","orcid":"https://orcid.org/0000-0003-0656-9874"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shang-Wen Li","raw_affiliation_strings":["Amazon AI"],"affiliations":[{"raw_affiliation_string":"Amazon AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-yi Lee","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5069156649"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":20.4383,"has_fulltext":false,"cited_by_count":162,"citation_normalized_percentile":{"value":0.99534334,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"344","last_page":"350"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9990000128746033,"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/T10028","display_name":"Topic Modeling","score":0.9983999729156494,"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":0.8106896281242371},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6240026950836182},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.621914803981781},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.5628465414047241},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.5586726665496826},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5201326012611389},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5193641781806946},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45959338545799255},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.44334882497787476},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4321700930595398},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3756878972053528},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3248724341392517}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8106896281242371},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6240026950836182},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.621914803981781},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.5628465414047241},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.5586726665496826},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5201326012611389},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5193641781806946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45959338545799255},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.44334882497787476},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4321700930595398},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3756878972053528},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3248724341392517},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","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/slt48900.2021.9383575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2187089797","https://openalex.org/W2747874407","https://openalex.org/W2842511635","https://openalex.org/W2866343820","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2948947170","https://openalex.org/W2962739339","https://openalex.org/W2963341956","https://openalex.org/W2963347649","https://openalex.org/W2963928591","https://openalex.org/W2965046076","https://openalex.org/W2965373594","https://openalex.org/W2970597249","https://openalex.org/W2972808286","https://openalex.org/W2972889948","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W2981991061","https://openalex.org/W2982223350","https://openalex.org/W2996383576","https://openalex.org/W2996428491","https://openalex.org/W3005680577","https://openalex.org/W3015265920","https://openalex.org/W3015412285","https://openalex.org/W3035524453","https://openalex.org/W3096485810","https://openalex.org/W4297808394","https://openalex.org/W6753640285","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6763701032","https://openalex.org/W6766673545","https://openalex.org/W6768021236","https://openalex.org/W6769196770","https://openalex.org/W6769238691","https://openalex.org/W6769686700","https://openalex.org/W6774314701"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W2992378684","https://openalex.org/W2964829415","https://openalex.org/W642007152","https://openalex.org/W2122233706","https://openalex.org/W2105439218","https://openalex.org/W3143423642","https://openalex.org/W2131711534","https://openalex.org/W2341426843"],"abstract_inverted_index":{"Self-supervised":[0],"speech":[1,5,35],"models":[2,13,78],"are":[3],"powerful":[4],"representation":[6,36,42],"extractors":[7],"for":[8,108,121,130],"downstream":[9,46,67,122],"applications.":[10],"Recently,":[11],"larger":[12],"have":[14],"been":[15],"utilized":[16],"in":[17,65,99],"acoustic":[18],"model":[19],"training":[20],"to":[21,44,79,134],"achieve":[22,135],"better":[23,136],"performance.":[24],"We":[25,38,53,93],"propose":[26],"Audio":[27,56,103],"ALBERT,":[28],"a":[29,127],"lite":[30],"version":[31],"of":[32,102],"the":[33,40,66,83,88,96,114],"self-supervised":[34,132],"model.":[37],"apply":[39],"lightweight":[41],"extractor":[43],"two":[45],"tasks,":[47],"speaker":[48,112],"classification":[49],"and":[50,90,111,138],"phoneme":[51,110],"classification.":[52],"show":[54],"that":[55,95],"ALBERT":[57,104],"achieves":[58],"performance":[59,137],"comparable":[60],"with":[61],"massive":[62],"pre-trained":[63],"networks":[64,133],"tasks":[68],"while":[69],"having":[70],"91%":[71],"fewer":[72],"parameters.":[73],"Moreover,":[74],"we":[75],"design":[76],"probing":[77],"measure":[80],"how":[81],"much":[82],"latent":[84],"representations":[85,97],"can":[86],"encode":[87],"speaker's":[89],"phoneme's":[91],"information.":[92],"find":[94],"encoded":[98],"internal":[100],"layers":[101],"contain":[105],"more":[106],"information":[107],"both":[109],"than":[113],"last":[115],"layer,":[116],"which":[117],"is":[118],"generally":[119],"used":[120],"tasks.":[123],"Our":[124],"findings":[125],"provide":[126],"new":[128],"avenue":[129],"using":[131],"efficiency.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":23},{"year":2023,"cited_by_count":38},{"year":2022,"cited_by_count":47},{"year":2021,"cited_by_count":38},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}