{"id":"https://openalex.org/W3197478142","doi":"https://doi.org/10.21437/interspeech.2021-1983","title":"WeNet: Production Oriented Streaming and Non-Streaming End-to-End Speech Recognition Toolkit","display_name":"WeNet: Production Oriented Streaming and Non-Streaming End-to-End Speech Recognition Toolkit","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197478142","doi":"https://doi.org/10.21437/interspeech.2021-1983","mag":"3197478142"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1983","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1983","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5109482068","display_name":"Zhuoyuan Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhuoyuan Yao","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","WeNet Open Source Community"],"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100602151","display_name":"Di Wu","orcid":"https://orcid.org/0000-0002-7788-9202"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Di Wu","raw_affiliation_strings":["Mobvoi Inc., Beijing, China,","WeNet Open Source Community"],"affiliations":[{"raw_affiliation_string":"Mobvoi Inc., Beijing, China,","institution_ids":[]},{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100359243","display_name":"Xiong Wang","orcid":"https://orcid.org/0000-0002-4091-5534"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiong Wang","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100449712","display_name":"Binbin Zhang","orcid":"https://orcid.org/0000-0002-1874-1881"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Binbin Zhang","raw_affiliation_strings":["WeNet Open Source Community","Mobvoi Inc., Beijing, China,"],"affiliations":[{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":[]},{"raw_affiliation_string":"Mobvoi Inc., Beijing, China,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100616400","display_name":"Fan Yu","orcid":"https://orcid.org/0000-0002-0576-7396"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Yu","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083993732","display_name":"Chao Yang","orcid":"https://orcid.org/0000-0002-9658-050X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Yang","raw_affiliation_strings":["WeNet Open Source Community","Mobvoi Inc., Beijing, China,"],"affiliations":[{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":[]},{"raw_affiliation_string":"Mobvoi Inc., Beijing, China,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041630666","display_name":"Zhendong Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhendong Peng","raw_affiliation_strings":["Mobvoi Inc., Beijing, China,","WeNet Open Source Community"],"affiliations":[{"raw_affiliation_string":"Mobvoi Inc., Beijing, China,","institution_ids":[]},{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100386496","display_name":"Xiaoyu Chen","orcid":"https://orcid.org/0000-0002-8576-1751"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoyu Chen","raw_affiliation_strings":["Mobvoi Inc., Beijing, China,","WeNet Open Source Community"],"affiliations":[{"raw_affiliation_string":"Mobvoi Inc., Beijing, China,","institution_ids":[]},{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049457213","display_name":"Xin Lei","orcid":"https://orcid.org/0000-0002-4400-4068"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Lei","raw_affiliation_strings":["Mobvoi Inc., Beijing, China,"],"affiliations":[{"raw_affiliation_string":"Mobvoi Inc., Beijing, China,","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5109482068"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":21.6849,"has_fulltext":false,"cited_by_count":208,"citation_normalized_percentile":{"value":0.99583581,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4054","last_page":"4058"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9889000058174133,"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":0.9768999814987183,"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":0.7556561231613159},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5573157072067261},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.5538901090621948},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4603239595890045},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.24617162346839905}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7556561231613159},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5573157072067261},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.5538901090621948},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4603239595890045},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.24617162346839905},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-1983","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1983","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1524333225","https://openalex.org/W1586532344","https://openalex.org/W1828163288","https://openalex.org/W1855892484","https://openalex.org/W2143612262","https://openalex.org/W2193413348","https://openalex.org/W2526425061","https://openalex.org/W2605141709","https://openalex.org/W2750499125","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2963242190","https://openalex.org/W3011207290","https://openalex.org/W3011339933","https://openalex.org/W3015457435","https://openalex.org/W3038006402","https://openalex.org/W3092122846","https://openalex.org/W3093346109","https://openalex.org/W3097125541","https://openalex.org/W3097777922","https://openalex.org/W3141464856","https://openalex.org/W3144345593","https://openalex.org/W3151526698","https://openalex.org/W4294619417","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2368779261","https://openalex.org/W2778699561","https://openalex.org/W2971982237","https://openalex.org/W2938947737","https://openalex.org/W2312526371","https://openalex.org/W2954695182","https://openalex.org/W4224917401","https://openalex.org/W4303519918","https://openalex.org/W2600628583","https://openalex.org/W2771275309"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,115],"propose":[4],"an":[5,56,99],"open":[6,78],"source":[7,79],"speech":[8,30,52,62,81],"recognition":[9,31,53,63,82],"toolkit":[10,172],"called":[11],"WeNet,":[12],"in":[13,32,66,111,152],"which":[14,69,122],"a":[15,33,85,112,117,157],"new":[16],"two-pass":[17],"approach":[18],"named":[19],"U2":[20],"is":[21,40,70,173],"implemented":[22],"to":[23,41,59,76,102,126,156],"unify":[24],"streaming":[25,108],"and":[26,48,74,98,109,168],"non-streaming":[27,110,153,159],"endto-end":[28],"(E2E)":[29],"single":[34],"model.The":[35],"main":[36,72],"motivation":[37],"of":[38,50],"WeNet":[39],"close":[42],"the":[43,46,71,124,129,137],"gap":[44],"between":[45],"research":[47],"deployment":[49],"E2E":[51,80],"models.WeNet":[54],"provides":[55],"efficient":[57],"way":[58],"ship":[60],"automatic":[61],"(ASR)":[64],"applications":[65],"real-world":[67],"scenarios,":[68],"difference":[73],"advantage":[75],"other":[77],"toolkits.We":[83],"develop":[84],"hybird":[86],"connectionist":[87],"temporal":[88],"classification":[89],"(CTC)/attention":[90],"architecture":[91],"with":[92,132],"transformer":[93],"or":[94],"conformer":[95],"as":[96],"encoder":[97],"attention":[100,120],"decoder":[101],"rescore":[103],"th":[104],"CTC":[105],"hypotheses.To":[106],"achieve":[107],"unified":[113],"model,":[114],"use":[116],"dynamic":[118],"chunk-based":[119],"strategy":[121],"allows":[123],"self-attention":[125],"focus":[127],"on":[128,136],"right":[130],"context":[131],"random":[133],"length.Our":[134],"experiments":[135],"AISHELL-1":[138],"dataset":[139],"show":[140],"that":[141],"our":[142,163],"model":[143,161,164],"achieves":[144,165],"5.03%":[145],"relative":[146],"character":[147],"error":[148],"rate":[149],"(CER)":[150],"reduction":[151],"ASR":[154],"compared":[155],"standard":[158],"transformer.After":[160],"quantification,":[162],"reasonable":[166],"RTF":[167],"latency":[169],"at":[170,176],"runtime.The":[171],"publicly":[174],"available":[175],"https://github.com/mobvoi/wenet.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":50},{"year":2024,"cited_by_count":58},{"year":2023,"cited_by_count":58},{"year":2022,"cited_by_count":34},{"year":2021,"cited_by_count":4}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}