{"id":"https://openalex.org/W3097625183","doi":"https://doi.org/10.21437/interspeech.2020-1600","title":"Listen Attentively, and Spell Once: Whole Sentence Generation via a Non-Autoregressive Architecture for Low-Latency Speech Recognition","display_name":"Listen Attentively, and Spell Once: Whole Sentence Generation via a Non-Autoregressive Architecture for Low-Latency Speech Recognition","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3097625183","doi":"https://doi.org/10.21437/interspeech.2020-1600","mag":"3097625183"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1600","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1600","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/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":["School of Artificial Intelligence, University of Chinese Academy of Sciences, China","NLPR, Institute of Automation, Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"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, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, 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"]},{"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","NLPR, Institute of Automation, Chinese Academy of Sciences, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAS Center for Excellence in Brain Science and Intelligence Technology","institution_ids":["https://openalex.org/I4210097554"]},{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, China","institution_ids":["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, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, China","institution_ids":["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, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100328947","display_name":"Shuai Zhang","orcid":"https://orcid.org/0000-0003-4291-8170"},"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":"Shuai Zhang","raw_affiliation_strings":["NLPR, Institute of Automation, Chinese Academy of Sciences, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, 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":5.281,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.96390257,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3381","last_page":"3385"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9900000095367432,"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":0.9825999736785889,"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":0.7530004978179932},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7180870771408081},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5228172540664673},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.479788601398468},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4547015130519867},{"id":"https://openalex.org/keywords/spell","display_name":"Spell","score":0.44692960381507874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3999510407447815},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08413335680961609},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07489624619483948}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7530004978179932},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7180870771408081},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5228172540664673},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.479788601398468},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4547015130519867},{"id":"https://openalex.org/C2780957641","wikidata":"https://www.wikidata.org/wiki/Q1999796","display_name":"Spell","level":2,"score":0.44692960381507874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3999510407447815},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08413335680961609},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07489624619483948},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1600","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1600","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/16"}],"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/G7331290385","display_name":null,"funder_award_id":"2016YFB1001404","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":24,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W2194775991","https://openalex.org/W2201092681","https://openalex.org/W2327501763","https://openalex.org/W2407080277","https://openalex.org/W2514741789","https://openalex.org/W2526425061","https://openalex.org/W2567070169","https://openalex.org/W2767206889","https://openalex.org/W2892009249","https://openalex.org/W2936774411","https://openalex.org/W2962826786","https://openalex.org/W2963242190","https://openalex.org/W2963434219","https://openalex.org/W2963807318","https://openalex.org/W2970832665","https://openalex.org/W2972818416","https://openalex.org/W2979636403","https://openalex.org/W2982095018","https://openalex.org/W2988975212","https://openalex.org/W3014413043","https://openalex.org/W4295312788","https://openalex.org/W4385245566","https://openalex.org/W4394666973"],"related_works":["https://openalex.org/W4287256643","https://openalex.org/W2745258745","https://openalex.org/W4296626305","https://openalex.org/W4254978807","https://openalex.org/W4307454463","https://openalex.org/W4287201819","https://openalex.org/W4230790962","https://openalex.org/W2808324063","https://openalex.org/W4239590911","https://openalex.org/W2808532741"],"abstract_inverted_index":{"Although":[0],"attention":[1,81],"based":[2,78,82],"end-to-end":[3,34],"models":[4],"have":[5],"achieved":[6],"promising":[7],"performance":[8],"in":[9,16,54,90],"speech":[10,35],"recognition,":[11],"the":[12,46,55,58,64,75,80,85,110,126],"multi-pass":[13],"forward":[14],"computation":[15,86],"beam-search":[17],"increases":[18],"inference":[19,69,117],"time":[20,70],"cost,":[21],"which":[22,108,122],"limits":[23],"their":[24],"practical":[25],"applications.To":[26],"address":[27],"this":[28],"issue,":[29],"we":[30],"propose":[31],"a":[32,51,102],"non-autoregressive":[33,47],"recognition":[36],"system":[37],"called":[38],"LASO":[39,49],"(listen":[40],"attentively,":[41],"and":[42],"spell":[43],"once).Because":[44],"of":[45,72,106,125],"property,":[48],"predicts":[50],"textual":[52],"token":[53],"sequence":[56],"without":[57],"dependence":[59],"on":[60,79,95],"other":[61],"tokens.Without":[62],"beam-search,":[63],"one-pass":[65],"propagation":[66],"much":[67],"reduces":[68],"cost":[71],"LASO.And":[73],"because":[74],"model":[76,114],"is":[77,119,123],"feedforward":[83],"structure,":[84],"can":[87],"be":[88],"implemented":[89],"parallel":[91],"efficiently.We":[92],"conduct":[93],"experiments":[94],"publicly":[96],"available":[97],"Chinese":[98],"dataset":[99],"AISHELL-1.LASO":[100],"achieves":[101],"character":[103],"error":[104],"rate":[105],"6.4%,":[107],"outperforms":[109],"state-of-the-art":[111],"autoregressive":[112,127],"transformer":[113,128],"(6.7%).The":[115],"average":[116],"latency":[118],"21":[120],"ms,":[121],"1/50":[124],"model.":[129]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}