{"id":"https://openalex.org/W3160345865","doi":"https://doi.org/10.1109/icassp39728.2021.9414539","title":"A Further Study of Unsupervised Pretraining for Transformer Based Speech Recognition","display_name":"A Further Study of Unsupervised Pretraining for Transformer Based Speech Recognition","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160345865","doi":"https://doi.org/10.1109/icassp39728.2021.9414539","mag":"3160345865"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414539","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414539","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5110582135","display_name":"Dongwei Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210150338","display_name":"Beijing Ditan Hospital","ror":"https://ror.org/05kkkes98","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210150338"]},{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongwei Jiang","raw_affiliation_strings":["Didi Chuxing,AI Labs,Beijing,China","AI Labs, Didi Chuxing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Didi Chuxing,AI Labs,Beijing,China","institution_ids":["https://openalex.org/I4210150338"]},{"raw_affiliation_string":"AI Labs, Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050050390","display_name":"Wubo Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210150338","display_name":"Beijing Ditan Hospital","ror":"https://ror.org/05kkkes98","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210150338"]},{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wubo Li","raw_affiliation_strings":["Didi Chuxing,AI Labs,Beijing,China","AI Labs, Didi Chuxing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Didi Chuxing,AI Labs,Beijing,China","institution_ids":["https://openalex.org/I4210150338"]},{"raw_affiliation_string":"AI Labs, Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029228290","display_name":"Ruixiong Zhang","orcid":"https://orcid.org/0000-0002-8597-8969"},"institutions":[{"id":"https://openalex.org/I4210150338","display_name":"Beijing Ditan Hospital","ror":"https://ror.org/05kkkes98","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210150338"]},{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruixiong Zhang","raw_affiliation_strings":["Didi Chuxing,AI Labs,Beijing,China","AI Labs, Didi Chuxing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Didi Chuxing,AI Labs,Beijing,China","institution_ids":["https://openalex.org/I4210150338"]},{"raw_affiliation_string":"AI Labs, Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010070743","display_name":"Miao Cao","orcid":"https://orcid.org/0000-0001-7254-5227"},"institutions":[{"id":"https://openalex.org/I4210150338","display_name":"Beijing Ditan Hospital","ror":"https://ror.org/05kkkes98","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210150338"]},{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miao Cao","raw_affiliation_strings":["Didi Chuxing,AI Labs,Beijing,China","AI Labs, Didi Chuxing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Didi Chuxing,AI Labs,Beijing,China","institution_ids":["https://openalex.org/I4210150338"]},{"raw_affiliation_string":"AI Labs, Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049649860","display_name":"Ne Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210150338","display_name":"Beijing Ditan Hospital","ror":"https://ror.org/05kkkes98","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210150338"]},{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ne Luo","raw_affiliation_strings":["Didi Chuxing,AI Labs,Beijing,China","AI Labs, Didi Chuxing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Didi Chuxing,AI Labs,Beijing,China","institution_ids":["https://openalex.org/I4210150338"]},{"raw_affiliation_string":"AI Labs, Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055058218","display_name":"Han Yang","orcid":"https://orcid.org/0000-0003-4469-6743"},"institutions":[{"id":"https://openalex.org/I4210150338","display_name":"Beijing Ditan Hospital","ror":"https://ror.org/05kkkes98","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210150338"]},{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Han","raw_affiliation_strings":["Didi Chuxing,AI Labs,Beijing,China","AI Labs, Didi Chuxing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Didi Chuxing,AI Labs,Beijing,China","institution_ids":["https://openalex.org/I4210150338"]},{"raw_affiliation_string":"AI Labs, Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108286207","display_name":"Wei Zou","orcid":"https://orcid.org/0000-0003-4215-5361"},"institutions":[{"id":"https://openalex.org/I4210150338","display_name":"Beijing Ditan Hospital","ror":"https://ror.org/05kkkes98","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210150338"]},{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zou","raw_affiliation_strings":["Didi Chuxing,AI Labs,Beijing,China","AI Labs, Didi Chuxing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Didi Chuxing,AI Labs,Beijing,China","institution_ids":["https://openalex.org/I4210150338"]},{"raw_affiliation_string":"AI Labs, Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101924647","display_name":"Kun Han","orcid":"https://orcid.org/0000-0003-2148-7594"},"institutions":[{"id":"https://openalex.org/I4210150338","display_name":"Beijing Ditan Hospital","ror":"https://ror.org/05kkkes98","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210150338"]},{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Han","raw_affiliation_strings":["Didi Chuxing,AI Labs,Beijing,China","AI Labs, Didi Chuxing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Didi Chuxing,AI Labs,Beijing,China","institution_ids":["https://openalex.org/I4210150338"]},{"raw_affiliation_string":"AI Labs, Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081173423","display_name":"Xiangang Li","orcid":"https://orcid.org/0000-0002-7810-1077"},"institutions":[{"id":"https://openalex.org/I4210150338","display_name":"Beijing Ditan Hospital","ror":"https://ror.org/05kkkes98","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210150338"]},{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangang Li","raw_affiliation_strings":["Didi Chuxing,AI Labs,Beijing,China","AI Labs, Didi Chuxing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Didi Chuxing,AI Labs,Beijing,China","institution_ids":["https://openalex.org/I4210150338"]},{"raw_affiliation_string":"AI Labs, Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6538","last_page":"6542"},"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":0.9973999857902527,"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":0.9966999888420105,"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":0.7808009386062622},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7693934440612793},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.746776819229126},{"id":"https://openalex.org/keywords/predictive-coding","display_name":"Predictive coding","score":0.6304376125335693},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.545437753200531},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48447370529174805},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.43319663405418396},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4319697916507721},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3553212583065033},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07768392562866211}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7808009386062622},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7693934440612793},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.746776819229126},{"id":"https://openalex.org/C2778061373","wikidata":"https://www.wikidata.org/wiki/Q1315146","display_name":"Predictive coding","level":3,"score":0.6304376125335693},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.545437753200531},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48447370529174805},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.43319663405418396},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4319697916507721},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3553212583065033},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07768392562866211},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414539","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414539","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W1494198834","https://openalex.org/W2149933564","https://openalex.org/W2168961642","https://openalex.org/W2327501763","https://openalex.org/W2515741950","https://openalex.org/W2526425061","https://openalex.org/W2560647685","https://openalex.org/W2563574619","https://openalex.org/W2842511635","https://openalex.org/W2902368158","https://openalex.org/W2911291251","https://openalex.org/W2926827382","https://openalex.org/W2927746189","https://openalex.org/W2935542736","https://openalex.org/W2936774411","https://openalex.org/W2939710050","https://openalex.org/W2945260553","https://openalex.org/W2962742956","https://openalex.org/W2963026768","https://openalex.org/W2963226322","https://openalex.org/W2963403868","https://openalex.org/W2963939538","https://openalex.org/W2964067969","https://openalex.org/W2964303116","https://openalex.org/W2965373594","https://openalex.org/W2971274815","https://openalex.org/W2972818416","https://openalex.org/W2972894903","https://openalex.org/W2972943112","https://openalex.org/W2973042454","https://openalex.org/W2973049979","https://openalex.org/W2973157397","https://openalex.org/W2979476256","https://openalex.org/W2980708516","https://openalex.org/W2981991061","https://openalex.org/W2982223350","https://openalex.org/W2988736778","https://openalex.org/W2996383576","https://openalex.org/W3003875258","https://openalex.org/W3007328579","https://openalex.org/W3015457435","https://openalex.org/W3016011332","https://openalex.org/W3016181583","https://openalex.org/W3041561163","https://openalex.org/W3096485810","https://openalex.org/W3102342027","https://openalex.org/W3148040514","https://openalex.org/W4288088457","https://openalex.org/W4297808394","https://openalex.org/W4299518610","https://openalex.org/W4385245566","https://openalex.org/W6603931906","https://openalex.org/W6682132143","https://openalex.org/W6726295259","https://openalex.org/W6739901393","https://openalex.org/W6762122294","https://openalex.org/W6766673545","https://openalex.org/W6769196770","https://openalex.org/W6769238691","https://openalex.org/W6769686700","https://openalex.org/W6769806307","https://openalex.org/W6770514103","https://openalex.org/W6773205534","https://openalex.org/W6777232839","https://openalex.org/W6780361010"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2110523656","https://openalex.org/W1482209366","https://openalex.org/W2521627374"],"abstract_inverted_index":{"The":[0,106],"construction":[1],"of":[2,13,57,83,149,161],"an":[3,134],"effective":[4],"good":[5],"speech":[6,43],"recognition":[7,44,123],"system":[8],"typically":[9],"requires":[10],"large":[11],"amounts":[12],"transcribed":[14],"data,":[15],"which":[16,163],"is":[17,118],"expensive":[18],"to":[19,61,103],"collect.":[20],"To":[21],"overcome":[22],"this":[23,66],"problem,":[24],"many":[25,55],"unsupervised":[26],"pretraining":[27,84,101,111],"methods":[28],"have":[29,59],"been":[30],"proposed.":[31],"Among":[32],"these":[33],"methods,":[34],"Masked":[35,48],"Predictive":[36],"Coding":[37],"achieved":[38],"significant":[39],"improvements":[40],"on":[41,73,77,90,121,139,144,169],"various":[42],"datasets":[45],"with":[46,113,129],"BERT-like":[47],"Reconstruction":[49],"loss":[50],"and":[51,75,93,131,153],"transformer":[52],"backbone.":[53],"However,":[54],"aspects":[56],"MPC":[58,74,132],"yet":[60],"be":[62],"fully":[63],"investigated.":[64],"In":[65],"paper,":[67],"we":[68],"conduct":[69],"a":[70,114,172],"further":[71],"study":[72],"focus":[76],"three":[78],"important":[79],"aspects:":[80],"the":[81,140,147,158],"effect":[82],"data":[85,112,151],"speaking":[86,116],"style,":[87],"its":[88],"extension":[89],"streaming":[91,141],"model,":[92],"strategies":[94],"for":[95],"better":[96],"transferring":[97],"learned":[98],"knowledge":[99,159],"from":[100],"stage":[102],"downstream":[104,122],"tasks.":[105,124],"experimental":[107],"results":[108],"demonstrated":[109],"that":[110],"matching":[115],"style":[117],"more":[119],"useful":[120],"A":[125],"unified":[126],"training":[127,156],"objective":[128],"APC":[130],"provided":[133],"8.46%":[135],"relative":[136,166],"error":[137,167],"reduction":[138,168],"model":[142],"trained":[143],"HKUST.":[145],"Additionally,":[146],"combination":[148],"target":[150],"adaption":[152],"layerwise":[154],"discriminative":[155],"facilitated":[157],"transfer":[160],"MPC,":[162],"realized":[164],"3.99%":[165],"AISHELL":[170],"over":[171],"strong":[173],"baseline.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}