{"id":"https://openalex.org/W4224917162","doi":"https://doi.org/10.1109/icassp43922.2022.9746067","title":"Non-Autoregressive End-To-End Automatic Speech Recognition Incorporating Downstream Natural Language Processing","display_name":"Non-Autoregressive End-To-End Automatic Speech Recognition Incorporating Downstream Natural Language Processing","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224917162","doi":"https://doi.org/10.1109/icassp43922.2022.9746067"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746067","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":"conference-paper","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/A5088171135","display_name":"Motoi Omachi","orcid":"https://orcid.org/0000-0002-9159-4371"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Motoi Omachi","raw_affiliation_strings":["Yahoo Japan Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Japan Corporation","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040732498","display_name":"Yuya Fujita","orcid":"https://orcid.org/0000-0001-8155-6040"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuya Fujita","raw_affiliation_strings":["Yahoo Japan Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Japan Corporation","institution_ids":[]}]},{"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/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106407750","display_name":"Tianzi Wang","orcid":"https://orcid.org/0009-0005-5823-3039"},"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":"Tianzi Wang","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"ii","issue":null,"first_page":"6772","last_page":"6776"},"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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":0.8547285199165344},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7009315490722656},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6552819013595581},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6524252891540527},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.6113495826721191},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5958223938941956},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5109816789627075},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4829658567905426},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.43817752599716187},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.41856417059898376},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.4117392599582672},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4108121395111084},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.12753060460090637},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07981398701667786}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8547285199165344},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7009315490722656},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6552819013595581},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6524252891540527},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6113495826721191},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5958223938941956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5109816789627075},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4829658567905426},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.43817752599716187},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.41856417059898376},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.4117392599582672},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4108121395111084},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.12753060460090637},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07981398701667786},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746067","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W37526647","https://openalex.org/W854541894","https://openalex.org/W1660460062","https://openalex.org/W2102113734","https://openalex.org/W2143612262","https://openalex.org/W2327501763","https://openalex.org/W2575406636","https://openalex.org/W2618015847","https://openalex.org/W2886180730","https://openalex.org/W2889320445","https://openalex.org/W2892009249","https://openalex.org/W2914417638","https://openalex.org/W2962760690","https://openalex.org/W2962780374","https://openalex.org/W2963070863","https://openalex.org/W2963250244","https://openalex.org/W2972389417","https://openalex.org/W2972451902","https://openalex.org/W2988975212","https://openalex.org/W3010788072","https://openalex.org/W3014413043","https://openalex.org/W3035445001","https://openalex.org/W3095918555","https://openalex.org/W3096160024","https://openalex.org/W3097882114","https://openalex.org/W3100460087","https://openalex.org/W3162249256","https://openalex.org/W3171851140","https://openalex.org/W3197140813","https://openalex.org/W3197304116","https://openalex.org/W4385245566","https://openalex.org/W6601563604","https://openalex.org/W6623517193","https://openalex.org/W6637201659","https://openalex.org/W6675365184","https://openalex.org/W6732408451","https://openalex.org/W6739901393","https://openalex.org/W6754299077","https://openalex.org/W6774835902","https://openalex.org/W6775187155"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1732468982","https://openalex.org/W1761388607","https://openalex.org/W2962716343","https://openalex.org/W2765804957","https://openalex.org/W2049117375","https://openalex.org/W43702919","https://openalex.org/W2060410964","https://openalex.org/W845924147"],"abstract_inverted_index":{"We":[0,46,70],"propose":[1],"a":[2,26,97,134],"fast":[3],"and":[4,15,31,39,96,102,114,124,144,159,172],"accurate":[5],"end-to-end":[6],"(E2E)":[7],"model,":[8],"which":[9],"executes":[10],"automatic":[11],"speech":[12],"recognition":[13],"(ASR)":[14],"downstream":[16,125],"natural":[17],"language":[18,100],"processing":[19],"(NLP)":[20],"simultaneously.":[21],"The":[22,117],"proposed":[23,118,153],"approach":[24],"predicts":[25],"single-aligned":[27,85],"sequence":[28,86],"of":[29,52,94,141],"transcriptions":[30,158],"linguistic":[32,160],"annotations":[33,161],"such":[34],"as":[35],"part-of-speech":[36],"(POS)":[37],"tags":[38,43],"named":[40],"entity":[41],"(NE)":[42],"from":[44],"speech.":[45],"use":[47,71],"non-autoregressive":[48],"(NAR)":[49],"decoding":[50,55,171],"instead":[51],"autoregressive":[53],"(AR)":[54],"to":[56,82],"reduce":[57],"execution":[58],"time":[59],"since":[60],"NAR":[61,135],"can":[62,156],"output":[63,104,112],"multiple":[64],"tokens":[65,105,113],"in":[66,133],"parallel":[67],"across":[68],"time.":[69],"the":[72,84,122,139,152],"connectionist":[73],"temporal":[74],"classification":[75],"(CTC)":[76],"model":[77,101,155],"with":[78,106,162],"mask-predict,":[79],"i.e.,":[80,128],"Mask-CTC,":[81],"predict":[83,157],"accurately.":[87],"Mask-CTC":[88],"improves":[89],"performance":[90,165],"by":[91],"joint":[92],"training":[93],"CTC":[95,168],"conditioned":[98,109],"masked":[99],"refining":[103],"low":[107],"confidence":[108],"on":[110],"reliable":[111],"audio":[115],"embeddings.":[116],"method":[119],"jointly":[120],"performs":[121],"ASR":[123],"NLP":[126],"task,":[127],"POS":[129],"or":[130],"NE":[131],"tagging,":[132],"manner.":[136],"Experiments":[137],"using":[138,169],"Corpus":[140],"Spontaneous":[142],"Japanese":[143],"Spoken":[145],"Language":[146],"Understanding":[147],"Resource":[148],"Package":[149],"show":[150],"that":[151],"E2E":[154],"consistently":[163],"better":[164],"than":[166,175],"vanilla":[167],"greedy":[170],"15\u201397x":[173],"faster":[174],"Transformer-based":[176],"AR":[177],"model.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}