{"id":"https://openalex.org/W3200006799","doi":"https://doi.org/10.1109/icassp43922.2022.9746903","title":"Non-Autoregressive Transformer with Unified Bidirectional Decoder for Automatic Speech Recognition","display_name":"Non-Autoregressive Transformer with Unified Bidirectional Decoder for Automatic Speech Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3200006799","doi":"https://doi.org/10.1109/icassp43922.2022.9746903","mag":"3200006799"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746903","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746903","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5015331058","display_name":"Chuanfei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chuan-Fei Zhang","raw_affiliation_strings":["University of Science and Technology Beijing,School of Automation and Electrical Engineering,Beijing,China,100083","Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing,School of Automation and Electrical Engineering,Beijing,China,100083","institution_ids":["https://openalex.org/I92403157"]},{"raw_affiliation_string":"Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100351068","display_name":"Yan Liu","orcid":"https://orcid.org/0000-0002-3108-3721"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Liu","raw_affiliation_strings":["University of Science and Technology Beijing,School of Automation and Electrical Engineering,Beijing,China,100083","Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing,School of Automation and Electrical Engineering,Beijing,China,100083","institution_ids":["https://openalex.org/I92403157"]},{"raw_affiliation_string":"Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669565","display_name":"Tianhao Zhang","orcid":"https://orcid.org/0000-0002-5939-3932"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian-Hao Zhang","raw_affiliation_strings":["University of Science and Technology Beijing,USTB-EEasyTech Joint Lab of Artificial Intelligence,Beijing,China,100083"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing,USTB-EEasyTech Joint Lab of Artificial Intelligence,Beijing,China,100083","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006074341","display_name":"Song-Lu Chen","orcid":"https://orcid.org/0000-0002-0780-658X"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song-Lu Chen","raw_affiliation_strings":["University of Science and Technology Beijing,USTB-EEasyTech Joint Lab of Artificial Intelligence,Beijing,China,100083"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing,USTB-EEasyTech Joint Lab of Artificial Intelligence,Beijing,China,100083","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048457230","display_name":"Chen Feng","orcid":"https://orcid.org/0000-0003-4971-4322"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Chen","raw_affiliation_strings":["University of Science and Technology Beijing,USTB-EEasyTech Joint Lab of Artificial Intelligence,Beijing,China,100083","EEasy Technology Company Ltd., Zhuhai, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing,USTB-EEasyTech Joint Lab of Artificial Intelligence,Beijing,China,100083","institution_ids":["https://openalex.org/I92403157"]},{"raw_affiliation_string":"EEasy Technology Company Ltd., Zhuhai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074514262","display_name":"Xu-Cheng Yin","orcid":"https://orcid.org/0000-0003-0023-0220"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu-Cheng Yin","raw_affiliation_strings":["University of Science and Technology Beijing,USTB-EEasyTech Joint Lab of Artificial Intelligence,Beijing,China,100083"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing,USTB-EEasyTech Joint Lab of Artificial Intelligence,Beijing,China,100083","institution_ids":["https://openalex.org/I92403157"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5015331058"],"corresponding_institution_ids":["https://openalex.org/I92403157"],"apc_list":null,"apc_paid":null,"fwci":1.0394,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.77424047,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6527","last_page":"6531"},"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":0.9988999962806702,"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":0.9959999918937683,"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/autoregressive-model","display_name":"Autoregressive model","score":0.8360939621925354},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7277742624282837},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7188885807991028},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7160278558731079},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5031163096427917},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4397920072078705},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3542443513870239},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13667282462120056},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12515243887901306},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.12153682112693787},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.1127619743347168},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.06782948970794678}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.8360939621925354},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7277742624282837},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7188885807991028},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7160278558731079},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5031163096427917},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4397920072078705},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3542443513870239},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13667282462120056},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12515243887901306},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.12153682112693787},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.1127619743347168},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.06782948970794678},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746903","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746903","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2127141656","https://openalex.org/W2132083787","https://openalex.org/W2183341477","https://openalex.org/W2407080277","https://openalex.org/W2767206889","https://openalex.org/W2892009249","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2962824709","https://openalex.org/W2963242190","https://openalex.org/W2963403868","https://openalex.org/W2963434219","https://openalex.org/W2963807318","https://openalex.org/W2964089333","https://openalex.org/W2964121744","https://openalex.org/W2972389417","https://openalex.org/W3014413043","https://openalex.org/W3015162217","https://openalex.org/W3015927303","https://openalex.org/W3096160024","https://openalex.org/W3097345069","https://openalex.org/W3097625183","https://openalex.org/W3097874139","https://openalex.org/W3097882114","https://openalex.org/W3097904285","https://openalex.org/W3140684480","https://openalex.org/W3160622492","https://openalex.org/W3162431424","https://openalex.org/W3170405627","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6713762819","https://openalex.org/W6739901393","https://openalex.org/W6746208923","https://openalex.org/W6754299077","https://openalex.org/W6768288844","https://openalex.org/W6775187155","https://openalex.org/W6775291257","https://openalex.org/W6780226713","https://openalex.org/W6784509666","https://openalex.org/W6792627859","https://openalex.org/W6797037654"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W2967478618","https://openalex.org/W2997152889","https://openalex.org/W4385572700","https://openalex.org/W4307309205","https://openalex.org/W4288261899","https://openalex.org/W4384264648","https://openalex.org/W4389471172","https://openalex.org/W3016124757"],"abstract_inverted_index":{"Non-autoregressive":[0],"(NAR)":[1],"transformer":[2,16,52,88,176,187],"models":[3,17],"have":[4],"been":[5],"studied":[6],"intensively":[7],"in":[8,130,191],"automatic":[9],"speech":[10],"recognition":[11],"(ASR),":[12],"and":[13,100,144,149],"many":[14],"NAR":[15,51,175],"is":[18,32,46],"to":[19,24,63],"use":[20,107],"the":[21,29,35,40,49,56,75,80,117,124,128,131,168,185],"causal":[22,30],"mask":[23,31,143],"limit":[25],"token":[26],"dependencies.":[27],"However,":[28,105],"designed":[33],"for":[34,48,103,152],"left-to-right":[36,99],"decoding":[37,190],"process":[38],"of":[39,108,127,165],"non-parallel":[41],"autoregressive":[42],"(AR)":[43],"transformer,":[44],"which":[45,95,115],"inappropriate":[47],"parallel":[50],"since":[53],"it":[54],"ignores":[55],"right-to-left":[57,65,101],"contexts.":[58],"Some":[59],"methods":[60,73],"are":[61],"proposed":[62],"utilize":[64,98],"contexts":[66,102,110],"with":[67,89],"an":[68],"extra":[69],"decoder,":[70],"but":[71],"these":[72],"increase":[74],"model":[76],"complexity.":[77],"To":[78,134],"tackle":[79],"above":[81],"problems,":[82],"we":[83,138],"propose":[84,139],"a":[85,90,140,192],"new":[86],"non-autoregressive":[87],"unified":[91],"bidirectional":[92,109],"decoder":[93,118],"(NAT-UBD),":[94],"can":[96,120,159,180],"simultaneously":[97],"ASR.":[104],"direct":[106],"will":[111],"cause":[112],"information":[113,126,136],"leakage,":[114,137],"means":[116],"output":[119],"be":[121],"affected":[122],"by":[123],"character":[125,161],"input":[129],"same":[132],"position.":[133],"avoid":[135],"novel":[141],"attention":[142],"modify":[145],"vanilla":[146],"queries,":[147],"keys,":[148],"values":[150],"matrices":[151],"NAT-UBD.":[153],"Experimental":[154],"results":[155],"verify":[156],"that":[157],"NAT-UBD":[158,179],"achieve":[160],"error":[162],"rates":[163],"(CERs)":[164],"5.0%/5.5%":[166],"on":[167],"Aishell-1":[169],"dev/test":[170],"sets,":[171],"outperforming":[172],"all":[173],"previous":[174],"models.":[177],"Moreover,":[178],"run":[181],"49.8\u00d7":[182],"faster":[183],"than":[184],"AR":[186],"baseline":[188],"when":[189],"single":[193],"step.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}