{"id":"https://openalex.org/W3162899666","doi":"https://doi.org/10.1109/icassp39728.2021.9414198","title":"Improved Mask-CTC for Non-Autoregressive End-to-End ASR","display_name":"Improved Mask-CTC for Non-Autoregressive End-to-End ASR","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162899666","doi":"https://doi.org/10.1109/icassp39728.2021.9414198","mag":"3162899666"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/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":true,"raw_author_name":"Yosuke Higuchi","raw_affiliation_strings":["Waseda University, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040282669","display_name":"Hirofumi Inaguma","orcid":"https://orcid.org/0000-0003-0610-1251"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirofumi Inaguma","raw_affiliation_strings":["Kyoto University, Japan"],"affiliations":[{"raw_affiliation_string":"Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"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, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, USA","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":[{"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, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University, 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, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102017467"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":6.1184,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.96924235,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"8363","last_page":"8367"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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/T10028","display_name":"Topic Modeling","score":0.9958999752998352,"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":0.8234124183654785},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7328941822052002},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.6730479001998901},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5992062091827393},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5683979988098145},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5412286520004272},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.46649858355522156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45726311206817627},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.41005846858024597},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34236904978752136},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24033799767494202},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.18650779128074646}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8234124183654785},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7328941822052002},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6730479001998901},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5992062091827393},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5683979988098145},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5412286520004272},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.46649858355522156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45726311206817627},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.41005846858024597},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34236904978752136},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24033799767494202},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.18650779128074646},{"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/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"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":80,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1828163288","https://openalex.org/W2024490156","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2160815625","https://openalex.org/W2251321385","https://openalex.org/W2407080277","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/W2920538220","https://openalex.org/W2936774411","https://openalex.org/W2944255943","https://openalex.org/W2946200149","https://openalex.org/W2946375144","https://openalex.org/W2948981900","https://openalex.org/W2949644922","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2962824709","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963434219","https://openalex.org/W2963736842","https://openalex.org/W2963742216","https://openalex.org/W2963827914","https://openalex.org/W2964089333","https://openalex.org/W2964308564","https://openalex.org/W2970730223","https://openalex.org/W2970832665","https://openalex.org/W2971167892","https://openalex.org/W2972389417","https://openalex.org/W2972818416","https://openalex.org/W2973122799","https://openalex.org/W2988975212","https://openalex.org/W3000840023","https://openalex.org/W3007328579","https://openalex.org/W3012492057","https://openalex.org/W3014413043","https://openalex.org/W3015194534","https://openalex.org/W3015537910","https://openalex.org/W3035445001","https://openalex.org/W3037217258","https://openalex.org/W3095173472","https://openalex.org/W3096160024","https://openalex.org/W3096664139","https://openalex.org/W3097777922","https://openalex.org/W3097874139","https://openalex.org/W3097882114","https://openalex.org/W3100753857","https://openalex.org/W3103005696","https://openalex.org/W3115011379","https://openalex.org/W4289440825","https://openalex.org/W4385245566","https://openalex.org/W6631362777","https://openalex.org/W6638749077","https://openalex.org/W6675365184","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6691770337","https://openalex.org/W6713762819","https://openalex.org/W6739901393","https://openalex.org/W6741807409","https://openalex.org/W6746208923","https://openalex.org/W6754299077","https://openalex.org/W6754576867","https://openalex.org/W6755207826","https://openalex.org/W6760017253","https://openalex.org/W6762471145","https://openalex.org/W6763608318","https://openalex.org/W6763832098","https://openalex.org/W6773383770","https://openalex.org/W6774835902","https://openalex.org/W6775187155"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1761388607","https://openalex.org/W1997922073","https://openalex.org/W2604685715","https://openalex.org/W2412160900","https://openalex.org/W2136453575","https://openalex.org/W1596913645","https://openalex.org/W1024498263","https://openalex.org/W2504816413"],"abstract_inverted_index":{"For":[0],"real-world":[1],"deployment":[2],"of":[3,15,22,63,72,107,160,174],"automatic":[4],"speech":[5,178],"recognition":[6,58],"(ASR),":[7],"the":[8,20,70,79,105,114,131],"system":[9,30],"is":[10],"desired":[11],"to":[12,77,103,116,154,176],"be":[13],"capable":[14],"fast":[16,54],"inference":[17,55,161],"while":[18],"relieving":[19],"requirement":[21],"computational":[23],"resources.":[24],"The":[25],"recently":[26,86],"proposed":[27,87,132],"end-to-end":[28,177],"ASR":[29,127],"based":[31],"on":[32,125,146],"mask-predict":[33],"with":[34,157],"connectionist":[35],"temporal":[36],"classification":[37],"(CTC),":[38],"Mask-CTC,":[39,73],"fulfills":[40],"this":[41],"demand":[42],"by":[43,83,99],"generating":[44],"tokens":[45,120],"in":[46],"a":[47,85,108,138,171],"non-autoregressive":[48],"fashion.":[49],"While":[50],"Mask-CTC":[51,135,149,175],"achieves":[52,151],"remarkably":[53],"speed,":[56],"its":[57],"performance":[59,71],"falls":[60],"behind":[61],"that":[62,130],"conventional":[64],"autoregressive":[65],"(AR)":[66],"systems.":[67],"To":[68],"boost":[69],"we":[74,92],"first":[75],"propose":[76,93],"enhance":[78],"encoder":[80],"network":[81],"architecture":[82,88],"employing":[84],"called":[89],"Conformer.":[90],"Next,":[91],"new":[94],"training":[95],"and":[96],"decoding":[97],"methods":[98],"introducing":[100],"auxiliary":[101],"objective":[102],"predict":[104],"length":[106],"partial":[109],"target":[110],"sequence,":[111],"which":[112],"allows":[113],"model":[115,141],"delete":[117],"or":[118],"insert":[119],"during":[121],"inference.":[122],"Experimental":[123],"results":[124,153],"different":[126],"tasks":[128],"show":[129,170],"approaches":[133],"improve":[134],"significantly,":[136],"outperforming":[137],"standard":[139],"CTC":[140],"(15.5%":[142],"\u2192":[143],"9.1%":[144],"WER":[145],"WSJ).":[147],"Moreover,":[148],"now":[150],"competitive":[152],"AR":[155],"models":[156],"no":[158],"degradation":[159],"speed":[162],"(<":[163],"0.1":[164],"RTF":[165],"using":[166],"CPU).":[167],"We":[168],"also":[169],"potential":[172],"application":[173],"translation.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":18}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}