{"id":"https://openalex.org/W4375869292","doi":"https://doi.org/10.1109/icassp49357.2023.10096154","title":"Fast-U2++: Fast and Accurate End-to-End Speech Recognition in Joint CTC/Attention Frames","display_name":"Fast-U2++: Fast and Accurate End-to-End Speech Recognition in Joint CTC/Attention Frames","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869292","doi":"https://doi.org/10.1109/icassp49357.2023.10096154"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096154","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5027514862","display_name":"Chengdong Liang","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"]},{"id":"https://openalex.org/I4401726824","display_name":"Horizon Robotics (China)","ror":"https://ror.org/05cmv6g68","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726824"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chengdong Liang","raw_affiliation_strings":["Northwestern Polytechnical University,School of Marine Science and Technology,Xi&#x2019;an,China","WeNet Open Source Community","Horizon Robotics, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Marine Science and Technology,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":[]},{"raw_affiliation_string":"Horizon Robotics, Beijing, China","institution_ids":["https://openalex.org/I4401726824"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450091","display_name":"Xiao-Lei Zhang","orcid":"https://orcid.org/0000-0001-7694-193X"},"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":"Xiao-Lei Zhang","raw_affiliation_strings":["Northwestern Polytechnical University,School of Marine Science and Technology,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Marine Science and Technology,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100449716","display_name":"Binbin Zhang","orcid":"https://orcid.org/0000-0002-7164-5127"},"institutions":[{"id":"https://openalex.org/I4401726824","display_name":"Horizon Robotics (China)","ror":"https://ror.org/05cmv6g68","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726824"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"BinBin Zhang","raw_affiliation_strings":["Horizon Robotics,Beijing,China","WeNet Open Source Community","Horizon Robotics, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Horizon Robotics,Beijing,China","institution_ids":["https://openalex.org/I4401726824"]},{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":[]},{"raw_affiliation_string":"Horizon Robotics, Beijing, China","institution_ids":["https://openalex.org/I4401726824"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100599890","display_name":"Di Wu","orcid":"https://orcid.org/0000-0002-4753-8161"},"institutions":[{"id":"https://openalex.org/I4401726824","display_name":"Horizon Robotics (China)","ror":"https://ror.org/05cmv6g68","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726824"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Wu","raw_affiliation_strings":["Horizon Robotics,Beijing,China","Horizon Robotics, Beijing, China","WeNet Open Source Community"],"affiliations":[{"raw_affiliation_string":"Horizon Robotics,Beijing,China","institution_ids":["https://openalex.org/I4401726824"]},{"raw_affiliation_string":"Horizon Robotics, Beijing, China","institution_ids":["https://openalex.org/I4401726824"]},{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101523840","display_name":"Shengqiang Li","orcid":"https://orcid.org/0000-0002-0837-6366"},"institutions":[{"id":"https://openalex.org/I4401726824","display_name":"Horizon Robotics (China)","ror":"https://ror.org/05cmv6g68","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726824"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengqiang Li","raw_affiliation_strings":["Horizon Robotics,Beijing,China","Horizon Robotics, Beijing, China","WeNet Open Source Community"],"affiliations":[{"raw_affiliation_string":"Horizon Robotics,Beijing,China","institution_ids":["https://openalex.org/I4401726824"]},{"raw_affiliation_string":"Horizon Robotics, Beijing, China","institution_ids":["https://openalex.org/I4401726824"]},{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074833963","display_name":"Xingchen Song","orcid":"https://orcid.org/0009-0009-9516-5361"},"institutions":[{"id":"https://openalex.org/I4401726824","display_name":"Horizon Robotics (China)","ror":"https://ror.org/05cmv6g68","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726824"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingchen Song","raw_affiliation_strings":["Horizon Robotics,Beijing,China","Horizon Robotics, Beijing, China","WeNet Open Source Community"],"affiliations":[{"raw_affiliation_string":"Horizon Robotics,Beijing,China","institution_ids":["https://openalex.org/I4401726824"]},{"raw_affiliation_string":"Horizon Robotics, Beijing, China","institution_ids":["https://openalex.org/I4401726824"]},{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041630666","display_name":"Zhendong Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726824","display_name":"Horizon Robotics (China)","ror":"https://ror.org/05cmv6g68","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726824"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhendong Peng","raw_affiliation_strings":["Horizon Robotics,Beijing,China","Horizon Robotics, Beijing, China","WeNet Open Source Community"],"affiliations":[{"raw_affiliation_string":"Horizon Robotics,Beijing,China","institution_ids":["https://openalex.org/I4401726824"]},{"raw_affiliation_string":"Horizon Robotics, Beijing, China","institution_ids":["https://openalex.org/I4401726824"]},{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031150833","display_name":"Fuping Pan","orcid":"https://orcid.org/0000-0001-9171-0726"},"institutions":[{"id":"https://openalex.org/I4401726824","display_name":"Horizon Robotics (China)","ror":"https://ror.org/05cmv6g68","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726824"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuping Pan","raw_affiliation_strings":["Horizon Robotics,Beijing,China","Horizon Robotics, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Horizon Robotics,Beijing,China","institution_ids":["https://openalex.org/I4401726824"]},{"raw_affiliation_string":"Horizon Robotics, Beijing, China","institution_ids":["https://openalex.org/I4401726824"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5027514862"],"corresponding_institution_ids":["https://openalex.org/I17145004","https://openalex.org/I4401726824"],"apc_list":null,"apc_paid":null,"fwci":0.8728,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77893894,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T11309","display_name":"Music and Audio Processing","score":0.9973999857902527,"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/T10860","display_name":"Speech and Audio Processing","score":0.9968000054359436,"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":0.8607238531112671},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7461581230163574},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.744722843170166},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.705952525138855},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6631518602371216},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.510326087474823},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4722054898738861},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45903846621513367},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.4274861216545105},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.34697961807250977},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30563703179359436},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.18973666429519653}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8607238531112671},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7461581230163574},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.744722843170166},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.705952525138855},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6631518602371216},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.510326087474823},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4722054898738861},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45903846621513367},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.4274861216545105},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.34697961807250977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30563703179359436},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.18973666429519653},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096154","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1821462560","https://openalex.org/W1828163288","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2327501763","https://openalex.org/W2526425061","https://openalex.org/W2892009249","https://openalex.org/W2936774411","https://openalex.org/W3015194534","https://openalex.org/W3015671919","https://openalex.org/W3092970820","https://openalex.org/W3094667432","https://openalex.org/W3096123040","https://openalex.org/W3097125541","https://openalex.org/W3097777922","https://openalex.org/W3111562797","https://openalex.org/W3125815078","https://openalex.org/W3148986242","https://openalex.org/W3163203022","https://openalex.org/W3170405627","https://openalex.org/W3196784225","https://openalex.org/W3197478142","https://openalex.org/W3197654132","https://openalex.org/W4221167707","https://openalex.org/W4288088457","https://openalex.org/W6623517193","https://openalex.org/W6638523607","https://openalex.org/W6638749077","https://openalex.org/W6687566353","https://openalex.org/W6769806307","https://openalex.org/W6787040858","https://openalex.org/W6790121257","https://openalex.org/W6793772276","https://openalex.org/W6797037654"],"related_works":["https://openalex.org/W2151749779","https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W3179968364","https://openalex.org/W4385572700","https://openalex.org/W3001710912"],"abstract_inverted_index":{"Recently,":[0],"the":[1,52,68,76,81,92],"unified":[2],"streaming":[3,20,131],"and":[4,23,104,120],"non-streaming":[5],"two-pass":[6],"(U2/U2++)":[7],"end-to-end":[8],"model":[9,114],"for":[10],"speech":[11],"recognition":[12],"has":[13],"shown":[14],"great":[15],"performance":[16,77],"in":[17,55,67],"terms":[18],"of":[19,34,44,51,71,127],"capability,":[21],"accuracy":[22],"latency.":[24,40,95],"In":[25],"this":[26],"paper,":[27],"we":[28,85],"present":[29,97],"fast-U2++,":[30],"an":[31],"enhanced":[32],"version":[33],"U2++":[35],"to":[36,47,74,90,110,118],"further":[37],"reduce":[38,91],"partial":[39,49],"The":[41],"core":[42],"idea":[43],"fast-U2++":[45,112],"is":[46],"output":[48],"results":[50],"bottom":[53],"layers":[54,70],"its":[56,72],"encoder":[57,73],"with":[58,129],"a":[59,64,122,130],"small":[60,82],"chunk,":[61],"while":[62],"using":[63],"large":[65],"chunk":[66],"top":[69],"compensate":[75],"degradation":[78],"caused":[79],"by":[80],"chunk.":[83],"More-over,":[84],"use":[86],"knowledge":[87],"distillation":[88],"method":[89],"token":[93],"emission":[94],"We":[96],"extensive":[98],"experiments":[99],"on":[100],"Aishell-1":[101],"dataset.":[102],"Experiments":[103],"ablation":[105],"studies":[106],"show":[107],"that":[108],"compared":[109],"U2++,":[111],"reduces":[113],"latency":[115],"from":[116],"320ms":[117],"80ms,":[119],"achieves":[121],"character":[123],"error":[124],"rate":[125],"(CER)":[126],"5.06%":[128],"setup.":[132]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
