{"id":"https://openalex.org/W3207558756","doi":"https://doi.org/10.1109/asru51503.2021.9688137","title":"An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition","display_name":"An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W3207558756","doi":"https://doi.org/10.1109/asru51503.2021.9688137","mag":"3207558756"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688137","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688137","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5050058892","display_name":"Xuankai Chang","orcid":"https://orcid.org/0000-0002-5221-5412"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xuankai Chang","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059612504","display_name":"Takashi Maekaku","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takashi Maekaku","raw_affiliation_strings":["Yahoo Japan Corporation"],"affiliations":[{"raw_affiliation_string":"Yahoo Japan Corporation","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101783173","display_name":"Pengcheng Guo","orcid":"https://orcid.org/0009-0001-2388-5935"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I99418890","display_name":"Northwestern Polytechnic University","ror":"https://ror.org/05wn69s11","country_code":"US","type":"education","lineage":["https://openalex.org/I99418890"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Pengcheng Guo","raw_affiliation_strings":["Northwestern Poly technical University"],"affiliations":[{"raw_affiliation_string":"Northwestern Poly technical University","institution_ids":["https://openalex.org/I99418890","https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112122495","display_name":"Jing Shi","orcid":"https://orcid.org/0000-0003-3225-7145"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Shi","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067198078","display_name":"Yen-Ju Lu","orcid":"https://orcid.org/0000-0001-8400-4188"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yen-Ju Lu","raw_affiliation_strings":["Academia Sinica"],"affiliations":[{"raw_affiliation_string":"Academia Sinica","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048730867","display_name":"Aswin Shanmugam Subramanian","orcid":"https://orcid.org/0000-0003-4446-001X"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aswin Shanmugam Subramanian","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106407750","display_name":"Tianzi Wang","orcid":"https://orcid.org/0009-0005-5823-3039"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianzi Wang","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078898845","display_name":"Shu-Wen Yang","orcid":"https://orcid.org/0000-0001-5503-9410"},"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":"Shu-wen Yang","raw_affiliation_strings":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Academia Sinica"],"affiliations":[{"raw_affiliation_string":"Academia Sinica","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","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":["National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5050058892"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":4.9518,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.96452328,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"228","last_page":"235"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.9966999888420105,"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":0.8409026861190796},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6831232905387878},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6243489980697632},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.521709144115448},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.5094841122627258},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5072295665740967},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.48212385177612305},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4761781096458435},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.45918363332748413},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.45244425535202026},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39615851640701294}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8409026861190796},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6831232905387878},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6243489980697632},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.521709144115448},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.5094841122627258},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5072295665740967},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.48212385177612305},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4761781096458435},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.45918363332748413},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45244425535202026},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39615851640701294},{"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9688137","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688137","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G6824508365","display_name":null,"funder_award_id":"ACI-1548562,ACI-1445606","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1526236009","https://openalex.org/W1569447338","https://openalex.org/W1855892484","https://openalex.org/W1989314204","https://openalex.org/W2058094241","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2148613904","https://openalex.org/W2152790380","https://openalex.org/W2155273149","https://openalex.org/W2221409856","https://openalex.org/W2251321385","https://openalex.org/W2463955103","https://openalex.org/W2526425061","https://openalex.org/W2559260703","https://openalex.org/W2842511635","https://openalex.org/W2883725317","https://openalex.org/W2892009249","https://openalex.org/W2896457183","https://openalex.org/W2962780374","https://openalex.org/W2963242190","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963807318","https://openalex.org/W2964074409","https://openalex.org/W2972818416","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W2982223350","https://openalex.org/W2991213871","https://openalex.org/W2995181338","https://openalex.org/W2996383576","https://openalex.org/W3015522062","https://openalex.org/W3016181583","https://openalex.org/W3036601975","https://openalex.org/W3037217258","https://openalex.org/W3041561163","https://openalex.org/W3095292526","https://openalex.org/W3097286738","https://openalex.org/W3097777922","https://openalex.org/W3099782249","https://openalex.org/W3101648800","https://openalex.org/W3105169251","https://openalex.org/W3139918052","https://openalex.org/W3151851237","https://openalex.org/W3160799772","https://openalex.org/W3163793923","https://openalex.org/W3197580070","https://openalex.org/W3198694222","https://openalex.org/W3198858531","https://openalex.org/W4297808394","https://openalex.org/W4385245566","https://openalex.org/W6633847657","https://openalex.org/W6682948231","https://openalex.org/W6685380521","https://openalex.org/W6691770337","https://openalex.org/W6739901393","https://openalex.org/W6754299077","https://openalex.org/W6755207826","https://openalex.org/W6768009688","https://openalex.org/W6769196770","https://openalex.org/W6770506093","https://openalex.org/W6779752190","https://openalex.org/W6780218876","https://openalex.org/W6780361010","https://openalex.org/W6784776607","https://openalex.org/W6785749098","https://openalex.org/W6791904447"],"related_works":["https://openalex.org/W1485630101","https://openalex.org/W2498017833","https://openalex.org/W2086733238","https://openalex.org/W112744582","https://openalex.org/W4383046901","https://openalex.org/W3200635595","https://openalex.org/W3206821803","https://openalex.org/W2468514837","https://openalex.org/W2473759012","https://openalex.org/W2024622335"],"abstract_inverted_index":{"Self-supervised":[0],"pretraining":[1],"on":[2,35,43,70,78,97],"speech":[3,15,76,82,90],"data":[4,24],"has":[5],"achieved":[6],"a":[7,20,57],"lot":[8,21],"of":[9,13,22,39,74,109,118],"progress.":[10],"High-fidelity":[11],"representation":[12],"the":[14,37,71,94,110,119,145,152,161,171],"signal":[16],"is":[17],"learned":[18],"from":[19],"untranscribed":[23],"and":[25,92,100,160,176],"shows":[26],"promising":[27],"performance.":[28,136],"Recently,":[29],"there":[30],"are":[31,148],"several":[32],"works":[33],"focusing":[34],"evaluating":[36],"quality":[38],"self-supervised":[40],"pretrained":[41,75,89,122],"representations":[42,91,147],"various":[44,98],"tasks":[45],"with-out":[46],"domain":[47],"restriction,":[48],"e.g.":[49],"SUPERB.":[50],"However,":[51],"such":[52,150],"evaluations":[53],"do":[54],"not":[55],"provide":[56],"comprehensive":[58],"comparison":[59],"among":[60],"many":[61],"ASR":[62],"benchmark":[63],"corpora.":[64],"In":[65],"this":[66],"paper,":[67],"we":[68,138],"focus":[69],"general":[72],"applications":[73],"representations,":[77,123],"advanced":[79],"end-to-end":[80],"automatic":[81],"recognition":[83,135],"(E2E-ASR)":[84],"models.":[85],"We":[86],"select":[87],"sev-eral":[88],"present":[93],"experimental":[95],"results":[96],"open-source":[99],"publicly":[101],"available":[102],"corpora":[103],"for":[104,143],"E2E-ASR.":[105],"Without":[106],"any":[107],"modification":[108],"back-end":[111],"model":[112],"archi-tectures":[113],"or":[114,130,154],"training":[115],"strategy,":[116],"some":[117],"experiments":[120,175],"with":[121,127],"e.g.,":[124],"WSJ,":[125],"WSJ0-2mix":[126],"HuBERT,":[128],"reach":[129],"out-perform":[131],"current":[132],"state-of-the-art":[133],"(SOTA)":[134],"Moreover,":[137],"further":[139],"explore":[140],"more":[141],"scenarios":[142],"whether":[144],"pre-training":[146],"effective,":[149],"as":[151],"cross-language":[153],"overlapped":[155],"speech.":[156],"The":[157],"scripts,":[158],"configuratons":[159],"trained":[162],"mod-els":[163],"have":[164],"been":[165],"released":[166],"in":[167],"ESPnet":[168],"to":[169],"let":[170],"community":[172],"reproduce":[173],"our":[174],"improve":[177],"them.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-14T08:43:22.919905","created_date":"2025-10-10T00:00:00"}