{"id":"https://openalex.org/W3164692279","doi":"https://doi.org/10.1109/taslp.2021.3082299","title":"Fast End-to-End Speech Recognition Via Non-Autoregressive Models and Cross-Modal Knowledge Transferring From BERT","display_name":"Fast End-to-End Speech Recognition Via Non-Autoregressive Models and Cross-Modal Knowledge Transferring From BERT","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3164692279","doi":"https://doi.org/10.1109/taslp.2021.3082299","mag":"3164692279"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3082299","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3082299","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5100624455","display_name":"Ye Bai","orcid":"https://orcid.org/0000-0001-5533-6909"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Bai","raw_affiliation_strings":["NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, Beijing, China","NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China; University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5533-6909","affiliations":[{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China; University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078525423","display_name":"Jiangyan Yi","orcid":"https://orcid.org/0000-0003-2422-4618"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangyan Yi","raw_affiliation_strings":["NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China","NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China#TAB#"],"raw_orcid":"https://orcid.org/0000-0003-2422-4618","affiliations":[{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China#TAB#","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing, China","NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, Beijing, China","CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing, China; NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China; University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9344-6428","affiliations":[{"raw_affiliation_string":"CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing, China","institution_ids":["https://openalex.org/I4210097554"]},{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing, China; NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China; University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210097554","https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101817056","display_name":"Zhengkun Tian","orcid":"https://orcid.org/0000-0002-0469-3049"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengkun Tian","raw_affiliation_strings":["NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, Beijing, China","NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China; University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China; University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111856667","display_name":"Zhengqi Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengqi Wen","raw_affiliation_strings":["NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China","NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China#TAB#","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100328935","display_name":"Shuai Zhang","orcid":"https://orcid.org/0000-0003-2413-9587"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Zhang","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.8772,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.96732935,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"29","issue":null,"first_page":"1897","last_page":"1911"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9947999715805054,"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/T11309","display_name":"Music and Audio Processing","score":0.993399977684021,"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":0.7854392528533936},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.7608587741851807},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7549116611480713},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6812508702278137},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.616206705570221},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5690546035766602},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4745408296585083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4495294988155365},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32987895607948303},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07810705900192261}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7854392528533936},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7608587741851807},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7549116611480713},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6812508702278137},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.616206705570221},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5690546035766602},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4745408296585083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4495294988155365},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32987895607948303},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07810705900192261},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2021.3082299","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3082299","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2516531902","display_name":null,"funder_award_id":"2018YFB1005003","funder_id":"https://openalex.org/F4320336026","funder_display_name":"National Key Research and Development Program of China Stem Cell and Translational Research"},{"id":"https://openalex.org/G4596905535","display_name":null,"funder_award_id":"61901473, 61771472, 61773379","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5381013183","display_name":null,"funder_award_id":"61831022","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/F4320336026","display_name":"National Key Research and Development Program of China Stem Cell and Translational Research","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":102,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W1690739335","https://openalex.org/W1821462560","https://openalex.org/W1828163288","https://openalex.org/W1915251500","https://openalex.org/W2127141656","https://openalex.org/W2127411609","https://openalex.org/W2137918516","https://openalex.org/W2160815625","https://openalex.org/W2194775991","https://openalex.org/W2266728343","https://openalex.org/W2283195891","https://openalex.org/W2294370754","https://openalex.org/W2327501763","https://openalex.org/W2402040300","https://openalex.org/W2526425061","https://openalex.org/W2561238782","https://openalex.org/W2567070169","https://openalex.org/W2578392894","https://openalex.org/W2605141709","https://openalex.org/W2606780347","https://openalex.org/W2767193869","https://openalex.org/W2767206889","https://openalex.org/W2888779557","https://openalex.org/W2889048668","https://openalex.org/W2892009249","https://openalex.org/W2896457183","https://openalex.org/W2911291251","https://openalex.org/W2915716523","https://openalex.org/W2936123380","https://openalex.org/W2936774411","https://openalex.org/W2944255943","https://openalex.org/W2952254971","https://openalex.org/W2962739339","https://openalex.org/W2962778134","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2962969034","https://openalex.org/W2963211739","https://openalex.org/W2963242190","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963425185","https://openalex.org/W2963434219","https://openalex.org/W2963536265","https://openalex.org/W2963807318","https://openalex.org/W2963970792","https://openalex.org/W2964089333","https://openalex.org/W2964118293","https://openalex.org/W2964121744","https://openalex.org/W2964272710","https://openalex.org/W2965116050","https://openalex.org/W2967957126","https://openalex.org/W2970832665","https://openalex.org/W2970971581","https://openalex.org/W2972818416","https://openalex.org/W2972991710","https://openalex.org/W2976556660","https://openalex.org/W2979636403","https://openalex.org/W2981022124","https://openalex.org/W2982095018","https://openalex.org/W2990391581","https://openalex.org/W3004127093","https://openalex.org/W3007328579","https://openalex.org/W3010262726","https://openalex.org/W3014413043","https://openalex.org/W3015595164","https://openalex.org/W3015671919","https://openalex.org/W3040986370","https://openalex.org/W3096297644","https://openalex.org/W3096798607","https://openalex.org/W3097625183","https://openalex.org/W3097882114","https://openalex.org/W3103005696","https://openalex.org/W4294619417","https://openalex.org/W4295312788","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6637551013","https://openalex.org/W6638523607","https://openalex.org/W6638749077","https://openalex.org/W6640059789","https://openalex.org/W6678852649","https://openalex.org/W6712847557","https://openalex.org/W6730179637","https://openalex.org/W6731370813","https://openalex.org/W6735706088","https://openalex.org/W6736685754","https://openalex.org/W6739901393","https://openalex.org/W6746208923","https://openalex.org/W6747158283","https://openalex.org/W6754473786","https://openalex.org/W6755207826","https://openalex.org/W6766978945","https://openalex.org/W6768952226","https://openalex.org/W6770528390","https://openalex.org/W6771291481","https://openalex.org/W6775187155","https://openalex.org/W6779715462","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W2997152889","https://openalex.org/W2171218219","https://openalex.org/W4285141722"],"abstract_inverted_index":{"Attention-based":[0],"encoder-decoder":[1],"(AED)":[2],"models":[3],"have":[4],"achieved":[5],"promising":[6],"performance":[7,145,201],"in":[8,23,38,117,120],"speech":[9,54,68,99,162],"recognition.":[10],"However,":[11],"because":[12],"the":[13,42,71,82,86,92,97,118,124,144,185,190,195,200,203],"decoder":[14],"predicts":[15,114],"text":[16],"tokens":[17,37,116],"(such":[18],"as":[19],"characters":[20],"or":[21],"words)":[22],"an":[24,31,51],"autoregressive":[25,103,109,186],"manner,":[26],"it":[27],"is":[28,126],"difficult":[29],"for":[30],"AED":[32],"model":[33,56,65,83,113,141,173,197],"to":[34,75,136,142],"predict":[35],"all":[36,115],"parallel.":[39],"This":[40],"makes":[41],"inference":[43,125],"speed":[44],"relatively":[45],"slow.":[46],"In":[47],"contrast,":[48],"we":[49,129],"propose":[50,130],"end-to-end":[52],"non-autoregressive":[53],"recognition":[55],"called":[57],"LASO":[58,148],"(Listen":[59],"Attentively,":[60],"and":[61,165,180],"Spell":[62],"Once).":[63],"The":[64],"aggregates":[66],"encoded":[67],"features":[69],"into":[70],"hidden":[72,94],"representations":[73,95],"corresponding":[74],"each":[76],"token":[77,87,151],"with":[78,184],"attention":[79],"mechanisms.":[80],"Thus,":[81],"can":[84,198],"capture":[85],"relations":[88],"by":[89,149],"self-attention":[90],"on":[91,105,156],"aggregated":[93],"from":[96,194],"whole":[98],"signal":[100],"rather":[101],"than":[102],"modeling":[104],"tokens.":[106],"Without":[107],"explicitly":[108],"language":[110,140],"modeling,":[111],"this":[112],"sequence":[119],"parallel":[121],"so":[122],"that":[123,170],"efficient.":[127],"Moreover,":[128],"a":[131,138,175],"cross-modal":[132,191],"transfer":[133],"learning":[134],"method":[135],"use":[137],"text-modal":[139,196],"improve":[143,199],"of":[146,159,177,202],"speech-modal":[147,204],"aligning":[150],"semantics.":[152],"We":[153],"conduct":[154],"experiments":[155],"two":[157],"scales":[158],"public":[160],"Chinese":[161],"datasets":[163],"AISHELL-1":[164],"AISHELL-2.":[166],"Experimental":[167],"results":[168],"show":[169],"our":[171],"proposed":[172],"achieves":[174],"speedup":[176],"about":[178],"50\u00d7":[179],"competitive":[181],"performance,":[182],"compared":[183],"transformer":[187],"models.":[188],"And":[189],"knowledge":[192],"transferring":[193],"model.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":10}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}