{"id":"https://openalex.org/W3112157188","doi":"https://doi.org/10.1109/lsp.2020.3044547","title":"Non-Autoregressive Transformer for Speech Recognition","display_name":"Non-Autoregressive Transformer for Speech Recognition","publication_year":2020,"publication_date":"2020-12-14","ids":{"openalex":"https://openalex.org/W3112157188","doi":"https://doi.org/10.1109/lsp.2020.3044547","mag":"3112157188"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2020.3044547","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2020.3044547","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1911.04908","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071702566","display_name":"Nanxin Chen","orcid":"https://orcid.org/0000-0001-6698-1604"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nanxin Chen","raw_affiliation_strings":["Department of ECE, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0001-6698-1604","affiliations":[{"raw_affiliation_string":"Department of ECE, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Department of ECE, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-5970-8631","affiliations":[{"raw_affiliation_string":"Department of ECE, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057010207","display_name":"Jes\u00fas Villalba","orcid":"https://orcid.org/0000-0001-9459-8426"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jesus Villalba","raw_affiliation_strings":["Department of ECE, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0001-9459-8426","affiliations":[{"raw_affiliation_string":"Department of ECE, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027217976","display_name":"Piotr \u017belasko","orcid":"https://orcid.org/0000-0002-8245-0413"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piotr Zelasko","raw_affiliation_strings":["Center of Language and Speech Processing, Johns Hopkins University-Homewood Campus, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-8245-0413","affiliations":[{"raw_affiliation_string":"Center of Language and Speech Processing, Johns Hopkins University-Homewood Campus, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":["Department of ECE, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-4489-5753","affiliations":[{"raw_affiliation_string":"Department of ECE, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":7.6527,"has_fulltext":false,"cited_by_count":89,"citation_normalized_percentile":{"value":0.97855771,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"28","issue":null,"first_page":"121","last_page":"125"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9990000128746033,"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":0.998199999332428,"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":0.816145658493042},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.797966718673706},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7496029138565063},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7225334644317627},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6897357702255249},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6714646816253662},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5027806758880615},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4551503658294678},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3406901955604553},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15374857187271118},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06928247213363647},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06411018967628479}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.816145658493042},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.797966718673706},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7496029138565063},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7225334644317627},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6897357702255249},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6714646816253662},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5027806758880615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4551503658294678},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3406901955604553},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15374857187271118},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06928247213363647},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06411018967628479},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lsp.2020.3044547","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2020.3044547","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1911.04908","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.04908","pdf_url":"https://arxiv.org/pdf/1911.04908","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1911.04908","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.04908","pdf_url":"https://arxiv.org/pdf/1911.04908","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7599999904632568,"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":51,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1660460062","https://openalex.org/W2127141656","https://openalex.org/W2327501763","https://openalex.org/W2542835211","https://openalex.org/W2767206889","https://openalex.org/W2892009249","https://openalex.org/W2896457183","https://openalex.org/W2912937082","https://openalex.org/W2920538220","https://openalex.org/W2936774411","https://openalex.org/W2945260553","https://openalex.org/W2949644922","https://openalex.org/W2953345635","https://openalex.org/W2962780374","https://openalex.org/W2963242190","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963434219","https://openalex.org/W2963827914","https://openalex.org/W2970597249","https://openalex.org/W2971274815","https://openalex.org/W2972818416","https://openalex.org/W2982095018","https://openalex.org/W2985694911","https://openalex.org/W2988975212","https://openalex.org/W2991509857","https://openalex.org/W3007328579","https://openalex.org/W3024732798","https://openalex.org/W3034729383","https://openalex.org/W3035445001","https://openalex.org/W3097874139","https://openalex.org/W3097882114","https://openalex.org/W3103005696","https://openalex.org/W4294149591","https://openalex.org/W4385245566","https://openalex.org/W6621543089","https://openalex.org/W6623517193","https://openalex.org/W6637201659","https://openalex.org/W6728610325","https://openalex.org/W6739901393","https://openalex.org/W6741807409","https://openalex.org/W6746208923","https://openalex.org/W6759317646","https://openalex.org/W6760017253","https://openalex.org/W6762122294","https://openalex.org/W6770587305","https://openalex.org/W6774835902","https://openalex.org/W6779469704"],"related_works":["https://openalex.org/W2171218219","https://openalex.org/W1972271943","https://openalex.org/W2150410159","https://openalex.org/W4327525404","https://openalex.org/W3150905897","https://openalex.org/W4287185323","https://openalex.org/W4206178588","https://openalex.org/W3094491777","https://openalex.org/W3214715529","https://openalex.org/W4287635093"],"abstract_inverted_index":{"Very":[0],"deep":[1],"transformers":[2],"outperform":[3],"conventional":[4],"bidirectional":[5],"long":[6],"short-term":[7],"memory":[8],"networks":[9],"for":[10,48,155],"automatic":[11],"speech":[12,96],"recognition":[13],"(ASR)":[14],"by":[15,72,86],"a":[16,28,152],"significant":[17],"margin.":[18],"However,":[19],"being":[20],"autoregressive":[21,175],"models,":[22],"their":[23,32],"computational":[24],"complexity":[25],"is":[26,79,122],"still":[27],"prohibitive":[29],"factor":[30],"in":[31,158],"deployment":[33],"into":[34,97],"production":[35],"systems.":[36],"To":[37],"amend":[38],"this":[39],"problem,":[40],"we":[41,101],"study":[42],"two":[43],"different":[44],"non-autoregressive":[45,153],"transformer":[46,176],"structures":[47],"ASR:":[49],"Audio-Conditional":[50],"Masked":[51,57],"Language":[52,58],"Model":[53,59],"(A-CMLM)":[54],"and":[55,93,107,168],"Audio-Factorized":[56],"(A-FMLM).":[60],"When":[61],"training":[62],"these":[63],"frameworks,":[64],"the":[65,77,83,89,94,108,130,135,160,164,170,173],"decoder":[66],"input":[67,95],"tokens":[68,85,92,106,113],"are":[69],"randomly":[70],"replaced":[71],"special":[73],"mask":[74],"tokens.":[75],"Then,":[76],"network":[78,109,154],"optimized":[80],"to":[81,134,149],"predict":[82],"masked":[84,105],"taking":[87],"both":[88],"unmasked":[90],"context":[91],"consideration.":[98],"During":[99],"inference,":[100],"start":[102],"from":[103,129],"all":[104],"iteratively":[110],"predicts":[111],"missing":[112],"based":[114],"on":[115,138],"partial":[116],"results.":[117],"A":[118],"new":[119],"decoding":[120],"strategy":[121],"proposed":[123,161],"as":[124],"an":[125],"example,":[126],"which":[127],"starts":[128],"most":[131],"confident":[132],"predictions":[133],"rest.":[136],"Results":[137],"Mandarin":[139],"(AISHELL),":[140],"Japanese":[141],"(CSJ),":[142],"English":[143],"(LibriSpeech)":[144],"benchmarks":[145],"show":[146],"promising":[147],"results":[148],"train":[150],"such":[151],"ASR.":[156],"Especially":[157],"AISHELL,":[159],"method":[162],"outperformed":[163],"Kaldi":[165],"ASR":[166],"system":[167],"matched":[169],"performance":[171],"of":[172],"state-of-the-art":[174],"with":[177],"7\u00d7":[178],"speedup.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":25},{"year":2021,"cited_by_count":10}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2020-12-21T00:00:00"}