{"id":"https://openalex.org/W3154932257","doi":"https://doi.org/10.1109/taslp.2021.3066274","title":"Integrating Knowledge Into End-to-End Speech Recognition From External Text-Only Data","display_name":"Integrating Knowledge Into End-to-End Speech Recognition From External Text-Only Data","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3154932257","doi":"https://doi.org/10.1109/taslp.2021.3066274","mag":"3154932257"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3066274","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3066274","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/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":["University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5533-6909","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["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"],"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"]}]},{"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"]}],"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"],"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"]}]},{"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"],"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"]}]},{"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/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":["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"]}]},{"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":0.6997,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75542765,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"29","issue":null,"first_page":"1340","last_page":"1351"},"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":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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":0.7896996736526489},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6892375946044922},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6434164047241211},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6379165649414062},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6350754499435425},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5673505067825317},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5570731163024902},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5549206137657166},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5318721532821655},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.512486457824707},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3236454129219055}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7896996736526489},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6892375946044922},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6434164047241211},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6379165649414062},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6350754499435425},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5673505067825317},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5570731163024902},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5549206137657166},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5318721532821655},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.512486457824707},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3236454129219055},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2021.3066274","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3066274","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":[{"score":0.6899999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"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"},{"id":"https://openalex.org/G7264488544","display_name":"\u60c5\u611f\u8bed\u97f3\u97f3\u8272\u5206\u6790\u53ca\u8865\u507f\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61771472","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8374701036","display_name":null,"funder_award_id":"61901473","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G953811167","display_name":null,"funder_award_id":"61773379","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":98,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W1524579289","https://openalex.org/W1690739335","https://openalex.org/W1821462560","https://openalex.org/W1828163288","https://openalex.org/W1915251500","https://openalex.org/W1984635093","https://openalex.org/W2050971845","https://openalex.org/W2110006374","https://openalex.org/W2112739286","https://openalex.org/W2117278770","https://openalex.org/W2131342762","https://openalex.org/W2160451571","https://openalex.org/W2167717037","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2270070752","https://openalex.org/W2275115695","https://openalex.org/W2294370754","https://openalex.org/W2327501763","https://openalex.org/W2402040300","https://openalex.org/W2402146185","https://openalex.org/W2466062786","https://openalex.org/W2471933213","https://openalex.org/W2526425061","https://openalex.org/W2567070169","https://openalex.org/W2577366047","https://openalex.org/W2581377246","https://openalex.org/W2608339501","https://openalex.org/W2740586471","https://openalex.org/W2747917286","https://openalex.org/W2886776719","https://openalex.org/W2888779557","https://openalex.org/W2889048668","https://openalex.org/W2889181648","https://openalex.org/W2889504751","https://openalex.org/W2889796598","https://openalex.org/W2892009249","https://openalex.org/W2935811960","https://openalex.org/W2936774411","https://openalex.org/W2939111082","https://openalex.org/W2943845043","https://openalex.org/W2944073381","https://openalex.org/W2952613254","https://openalex.org/W2953356739","https://openalex.org/W2962739339","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2962894366","https://openalex.org/W2963240019","https://openalex.org/W2963242190","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963414781","https://openalex.org/W2963736842","https://openalex.org/W2963807318","https://openalex.org/W2963970792","https://openalex.org/W2964118293","https://openalex.org/W2964121744","https://openalex.org/W2965116050","https://openalex.org/W2969521066","https://openalex.org/W2970119519","https://openalex.org/W2970597249","https://openalex.org/W2972818416","https://openalex.org/W2972991710","https://openalex.org/W2981022124","https://openalex.org/W2982095018","https://openalex.org/W2991509857","https://openalex.org/W3007328579","https://openalex.org/W3094800360","https://openalex.org/W3097777922","https://openalex.org/W3163793923","https://openalex.org/W4297798436","https://openalex.org/W4385245566","https://openalex.org/W6621543089","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6631435780","https://openalex.org/W6637551013","https://openalex.org/W6638523607","https://openalex.org/W6638749077","https://openalex.org/W6640059789","https://openalex.org/W6677328538","https://openalex.org/W6712847557","https://openalex.org/W6712930963","https://openalex.org/W6731370813","https://openalex.org/W6732696085","https://openalex.org/W6737185392","https://openalex.org/W6739901393","https://openalex.org/W6754469826","https://openalex.org/W6754473786","https://openalex.org/W6763701032","https://openalex.org/W6766471354","https://openalex.org/W6770587305","https://openalex.org/W6780226713","https://openalex.org/W6784531339"],"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/W4285141722","https://openalex.org/W4387768015"],"abstract_inverted_index":{"Attention-based":[0],"encoder-decoder":[1],"(AED)":[2],"models":[3],"have":[4],"achieved":[5],"promising":[6],"performance":[7],"in":[8,95,106,126,199,253],"speech":[9],"recognition.":[10],"However,":[11],"because":[12],"of":[13,40,53,156,173,185,231,244],"the":[14,41,50,59,63,86,92,107,116,124,127,132,136,139,144,153,157,171,178,182,191,196,200,212,222,242,250],"end-to-end":[15],"training,":[16,190],"an":[17,82,162],"AED":[18,36,42,83,145,192,266],"model":[19,43,84,112,146,193,267],"is":[20,28,44,100,113,129,141],"usually":[21],"trained":[22,114],"with":[23,188,256,261],"speech-text":[24],"paired":[25],"data.":[26],"It":[27,118],"challenging":[29],"to":[30,78,143],"incorporate":[31],"external":[32,87,246],"text-only":[33,88,247],"data":[34,89,248],"into":[35,81,102,131],"models.":[37],"Another":[38],"issue":[39],"that":[45,123],"it":[46],"does":[47,215],"not":[48,216],"use":[49,152,208],"right":[51,183],"context":[52,94,155,180,184,198,252],"a":[54,69,96,110,174,254],"text":[55,128,158],"token":[56],"while":[57],"predicting":[58],"token.":[60],"To":[61,150],"alleviate":[62],"above":[64],"two":[65,103,229],"issues,":[66],"we":[67,160],"propose":[68,161],"unified":[70],"method":[71,99,214],"called":[72,164],"LST":[73,189],"(Learn":[74],"Spelling":[75],"from":[76,85,203],"Teachers)":[77],"integrate":[79],"knowledge":[80,125,140],"and":[90,181,236,249,265],"leverage":[91,195],"whole":[93,154,197,251],"sentence.":[97,201],"The":[98,238],"divided":[101],"stages.":[104],"First,":[105],"representation":[108],"stage,":[109,138],"language":[111],"on":[115,228],"text.":[117],"can":[119,194],"be":[120],"seen":[121],"as":[122],"compressed":[130],"LM.":[133],"Then,":[134],"at":[135,221],"transferring":[137],"transferred":[142],"via":[147],"teacher-student":[148],"learning.":[149],"further":[151],"sentence,":[159],"LM":[163,209],"causal":[165],"cloze":[166],"completer":[167],"(COR),":[168],"which":[169,207],"estimates":[170],"probability":[172],"token,":[175],"given":[176],"both":[177],"left":[179],"it.":[186],"Therefore,":[187],"Different":[202],"fusion":[204],"based":[205,268],"methods,":[206],"during":[210],"decoding,":[211],"proposed":[213,258],"increase":[217],"any":[218],"extra":[219],"complexity":[220],"inference":[223],"stage.":[224],"We":[225],"conduct":[226],"experiments":[227],"scales":[230],"public":[232],"Chinese":[233],"datasets":[234],"AISHELL-1":[235],"AISHELL-2.":[237],"experimental":[239],"results":[240],"demonstrate":[241],"effectiveness":[243],"leveraging":[245],"sentence":[255],"our":[257],"method,":[259],"compared":[260],"baseline":[262],"hybrid":[263],"systems":[264],"systems.":[269]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}