{"id":"https://openalex.org/W4388117860","doi":"https://doi.org/10.23919/eusipco58844.2023.10290112","title":"Mask-CTC-Based Encoder Pre-Training for Streaming End-to-End Speech Recognition","display_name":"Mask-CTC-Based Encoder Pre-Training for Streaming End-to-End Speech Recognition","publication_year":2023,"publication_date":"2023-09-04","ids":{"openalex":"https://openalex.org/W4388117860","doi":"https://doi.org/10.23919/eusipco58844.2023.10290112"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco58844.2023.10290112","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/eusipco58844.2023.10290112","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","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/A5015374865","display_name":"Huaibo Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Huaibo Zhao","raw_affiliation_strings":["Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102017467","display_name":"Yosuke Higuchi","orcid":"https://orcid.org/0000-0003-4500-8957"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yosuke Higuchi","raw_affiliation_strings":["Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109488356","display_name":"Yusuke Kida","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Kida","raw_affiliation_strings":["LINE Corporation,Tokyo,Japan","LINE Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"LINE Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I4210096607"]},{"raw_affiliation_string":"LINE Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I4210096607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087632404","display_name":"Tetsuji Ogawa","orcid":"https://orcid.org/0000-0002-7316-2073"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuji Ogawa","raw_affiliation_strings":["Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101188700","display_name":"Tetsunori Kobayashi","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsunori Kobayashi","raw_affiliation_strings":["Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5015374865"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13991487,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"56","last_page":"60"},"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":0.9998000264167786,"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":0.9988999962806702,"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":0.8329445123672485},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7984436750411987},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7199579477310181},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6947696208953857},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5062912702560425},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.49505510926246643},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.437646746635437},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3651977777481079},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3595670461654663},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1267724633216858},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09016692638397217},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06706789135932922}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8329445123672485},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7984436750411987},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7199579477310181},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6947696208953857},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5062912702560425},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.49505510926246643},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.437646746635437},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3651977777481079},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3595670461654663},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1267724633216858},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09016692638397217},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06706789135932922},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco58844.2023.10290112","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/eusipco58844.2023.10290112","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.550000011920929,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2024490156","https://openalex.org/W2064675550","https://openalex.org/W2127141656","https://openalex.org/W2160815625","https://openalex.org/W2327501763","https://openalex.org/W2747874407","https://openalex.org/W2892009249","https://openalex.org/W2936123380","https://openalex.org/W2936774411","https://openalex.org/W2962760690","https://openalex.org/W2962780374","https://openalex.org/W2963250244","https://openalex.org/W2972389417","https://openalex.org/W2988975212","https://openalex.org/W3007433671","https://openalex.org/W3015974384","https://openalex.org/W3016010032","https://openalex.org/W3097777922","https://openalex.org/W3097882114","https://openalex.org/W3133822476","https://openalex.org/W3148654612","https://openalex.org/W3161873870","https://openalex.org/W3162899666","https://openalex.org/W4210663600","https://openalex.org/W4297727296","https://openalex.org/W4319862213","https://openalex.org/W4385245566","https://openalex.org/W4387638421","https://openalex.org/W6623517193","https://openalex.org/W6675365184","https://openalex.org/W6691770337","https://openalex.org/W6755207826","https://openalex.org/W6802702050","https://openalex.org/W6846378636"],"related_works":["https://openalex.org/W3205411230","https://openalex.org/W4286899009","https://openalex.org/W3163341049","https://openalex.org/W9168048","https://openalex.org/W4300849822","https://openalex.org/W4376480820","https://openalex.org/W3155891479","https://openalex.org/W3029351463","https://openalex.org/W4296591952","https://openalex.org/W4308600690"],"abstract_inverted_index":{"Achieving":[0],"high":[1,78],"accuracy":[2,31,79],"with":[3,125],"low":[4,75],"latency":[5,76,156],"has":[6,69,90,99,106],"always":[7],"been":[8,70,92,101],"a":[9,25],"challenge":[10],"in":[11,34,73,158],"streaming":[12,26,40,64,134,159],"end-to-end":[13],"automatic":[14],"speech":[15],"recognition":[16],"(ASR)":[17],"systems.":[18],"By":[19],"attending":[20],"to":[21,51,111,154],"more":[22],"future":[23],"contexts,":[24,59],"ASR":[27],"model":[28,96],"achieves":[29],"higher":[30],"but":[32],"results":[33],"larger":[35],"latency,":[36],"which":[37,60,152],"hurts":[38],"the":[39,43,53,85,104,107,118,139,142,155],"performance.":[41],"In":[42],"Mask-CTC":[44],"framework,":[45],"an":[46],"encoder":[47,67,105],"network":[48],"is":[49,61],"trained":[50],"learn":[52],"feature":[54],"representation":[55],"that":[56,103],"anticipates":[57],"long-term":[58],"desirable":[62],"for":[63,80,94,123],"ASR.":[65,83,135,160],"Mask-CTC-based":[66,121],"pre-training":[68,122,144],"shown":[71],"beneficial":[72],"achieving":[74],"and":[77,131],"triggered":[81],"attention-based":[82],"However,":[84],"effectiveness":[86,119],"of":[87,120,141],"this":[88],"method":[89,145],"not":[91],"demonstrated":[93],"various":[95],"architectures,":[97,127],"nor":[98],"it":[100],"verified":[102],"expected":[108],"look-ahead":[109],"capability":[110],"reduce":[112],"latency.":[113],"This":[114],"study,":[115],"therefore,":[116],"examines":[117],"models":[124],"different":[126],"such":[128],"as":[129],"Transformer-Transducer":[130],"contextual":[132],"block":[133],"We":[136],"also":[137],"discuss":[138],"effect":[140],"proposed":[143],"on":[146],"obtaining":[147],"accurate":[148],"output":[149],"spike":[150],"timings,":[151],"contributes":[153],"reduction":[157]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}