{"id":"https://openalex.org/W3097882114","doi":"https://doi.org/10.21437/interspeech.2020-2404","title":"Mask CTC: Non-Autoregressive End-to-End ASR with CTC and Mask Predict","display_name":"Mask CTC: Non-Autoregressive End-to-End ASR with CTC and Mask Predict","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3097882114","doi":"https://doi.org/10.21437/interspeech.2020-2404","mag":"3097882114"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2404","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2404","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5102017467","display_name":"Yosuke Higuchi","orcid":"https://orcid.org/0000-0003-4500-8957"},"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":true,"raw_author_name":"Yosuke Higuchi","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","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":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","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":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087632404","display_name":"Tetsuji Ogawa","orcid":"https://orcid.org/0000-0002-7316-2073"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tetsuji Ogawa","raw_affiliation_strings":["School of Fundamental Science and Engineering"],"affiliations":[{"raw_affiliation_string":"School of Fundamental Science and Engineering","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101188700","display_name":"Tetsunori Kobayashi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tetsunori Kobayashi","raw_affiliation_strings":["School of Fundamental Science and Engineering"],"affiliations":[{"raw_affiliation_string":"School of Fundamental Science and Engineering","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102017467"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":13.4556,"has_fulltext":false,"cited_by_count":122,"citation_normalized_percentile":{"value":0.99058217,"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":"3655","last_page":"3659"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9886999726295471,"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":0.9794999957084656,"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/autoregressive-model","display_name":"Autoregressive model","score":0.6615493297576904},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5849965214729309},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4847571551799774},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38760906457901},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24456027150154114},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12249347567558289},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09305351972579956}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6615493297576904},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5849965214729309},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4847571551799774},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38760906457901},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24456027150154114},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12249347567558289},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09305351972579956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2404","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2404","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"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":31,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1660460062","https://openalex.org/W2024490156","https://openalex.org/W2102113734","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2327501763","https://openalex.org/W2526425061","https://openalex.org/W2739883972","https://openalex.org/W2767206889","https://openalex.org/W2892009249","https://openalex.org/W2892213699","https://openalex.org/W2896457183","https://openalex.org/W2936774411","https://openalex.org/W2946375144","https://openalex.org/W2949644922","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2963434219","https://openalex.org/W2963827914","https://openalex.org/W2970832665","https://openalex.org/W2972389417","https://openalex.org/W2972818416","https://openalex.org/W2988975212","https://openalex.org/W2989134874","https://openalex.org/W3000840023","https://openalex.org/W3034729383","https://openalex.org/W3035445001","https://openalex.org/W3100753857","https://openalex.org/W3103005696","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2028868645","https://openalex.org/W2778699561","https://openalex.org/W2184320951","https://openalex.org/W2971982237","https://openalex.org/W2938947737","https://openalex.org/W2312526371","https://openalex.org/W2092372975","https://openalex.org/W3197304116","https://openalex.org/W3141854550","https://openalex.org/W3184187848"],"abstract_inverted_index":{"We":[0],"present":[1],"Mask":[2,87,152],"CTC,":[3],"a":[4,15,64,93],"novel":[5],"non-autoregressive":[6,57],"end-to-end":[7],"automatic":[8],"speech":[9,147],"recognition":[10,148],"(ASR)":[11],"framework,":[12],"which":[13,69],"generates":[14],"sequence":[16,107],"by":[17,36],"refining":[18],"outputs":[19,114],"of":[20,45,67,99,183],"the":[21,43,51,54,105,111,122,126,141,155,168],"connectionist":[22],"temporal":[23],"classification":[24],"(CTC).Neural":[25],"sequence-to-sequence":[26],"models":[27,58],"are":[28,118,136,186],"usually":[29],"autoregressive:":[30],"each":[31],"output":[32,52,130],"token":[33],"is":[34,90,108],"generated":[35,40],"conditioning":[37,139],"on":[38,121,125,140,145,164],"previously":[39],"tokens,":[41,131],"at":[42,189],"cost":[44],"requiring":[46,171],"as":[47,50],"many":[48],"iterations":[49],"length.On":[53],"other":[55],"hand,":[56],"can":[59],"simultaneously":[60],"generate":[61],"tokens":[62,117,135],"within":[63],"constant":[65],"number":[66],"iterations,":[68],"results":[70,144],"in":[71,180],"significant":[72],"inference":[73,174],"time":[74,175],"reduction":[75],"and":[76,102,115,166],"better":[77],"suits":[78],"end-toend":[79],"ASR":[80],"model":[81,89,158],"for":[82],"real-world":[83],"scenarios.In":[84],"this":[85],"work,":[86],"CTC":[88,113,123,153,157],"trained":[91],"using":[92,176],"Transformer":[94],"encoder-decoder":[95],"with":[96,110],"joint":[97],"training":[98],"mask":[100],"prediction":[101],"CTC.During":[103],"inference,":[104],"target":[106],"initialized":[109],"greedy":[112],"low-confidence":[116,134],"masked":[119,133],"based":[120],"probabilities.Based":[124],"conditional":[127],"dependence":[128],"between":[129],"these":[132],"then":[137],"predicted":[138],"high-confidence":[142],"tokens.Experimental":[143],"different":[146],"tasks":[149],"show":[150],"that":[151],"outperforms":[154],"standard":[156],"(e.g.,":[159],"17.9%":[160],"\u2192":[161],"12.1%":[162],"WER":[163],"WSJ)":[165],"approaches":[167],"autoregressive":[169],"model,":[170],"much":[172],"less":[173],"CPUs":[177],"(0.07":[178],"RTF":[179],"Python":[181],"implementation).All":[182],"our":[184],"codes":[185],"publicly":[187],"available":[188],"https://github.com/espnet/espnet.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":26},{"year":2022,"cited_by_count":30},{"year":2021,"cited_by_count":38},{"year":2020,"cited_by_count":5}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}