{"id":"https://openalex.org/W3015737168","doi":"https://doi.org/10.1109/icassp40776.2020.9052940","title":"Sequence-Level Consistency Training for Semi-Supervised End-to-End Automatic Speech Recognition","display_name":"Sequence-Level Consistency Training for Semi-Supervised End-to-End Automatic Speech Recognition","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015737168","doi":"https://doi.org/10.1109/icassp40776.2020.9052940","mag":"3015737168"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9052940","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9052940","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5060644399","display_name":"Ryo Masumura","orcid":"https://orcid.org/0000-0002-2415-4149"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Masumura","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027118468","display_name":"Mana Ihori","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mana Ihori","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080550833","display_name":"Akihiko Takashima","orcid":"https://orcid.org/0000-0001-7361-4562"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akihiko Takashima","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087290011","display_name":"Takafumi Moriya","orcid":"https://orcid.org/0000-0003-1942-7250"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takafumi Moriya","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061074419","display_name":"Atsushi Ando","orcid":"https://orcid.org/0000-0002-3971-0654"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi Ando","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109365728","display_name":"Yusuke Shinohara","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Shinohara","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7054","last_page":"7058"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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":0.9979000091552734,"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/consistency","display_name":"Consistency (knowledge bases)","score":0.7498587965965271},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7203803658485413},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6297279000282288},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5660018920898438},{"id":"https://openalex.org/keywords/consistency-model","display_name":"Consistency model","score":0.49945855140686035},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49502724409103394},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4783993661403656},{"id":"https://openalex.org/keywords/data-consistency","display_name":"Data consistency","score":0.46185457706451416},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4376169443130493},{"id":"https://openalex.org/keywords/strong-consistency","display_name":"Strong consistency","score":0.4164830446243286},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35647425055503845},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22562715411186218},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1478467881679535},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.0723375678062439}],"concepts":[{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.7498587965965271},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7203803658485413},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6297279000282288},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5660018920898438},{"id":"https://openalex.org/C37279795","wikidata":"https://www.wikidata.org/wiki/Q2492305","display_name":"Consistency model","level":3,"score":0.49945855140686035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49502724409103394},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4783993661403656},{"id":"https://openalex.org/C93361087","wikidata":"https://www.wikidata.org/wiki/Q4426698","display_name":"Data consistency","level":2,"score":0.46185457706451416},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4376169443130493},{"id":"https://openalex.org/C31388003","wikidata":"https://www.wikidata.org/wiki/Q7624548","display_name":"Strong consistency","level":3,"score":0.4164830446243286},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35647425055503845},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22562715411186218},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1478467881679535},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.0723375678062439},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9052940","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9052940","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W37526647","https://openalex.org/W1942035323","https://openalex.org/W2327501763","https://openalex.org/W2521999726","https://openalex.org/W2597757402","https://openalex.org/W2608712415","https://openalex.org/W2645998928","https://openalex.org/W2746192915","https://openalex.org/W2883586237","https://openalex.org/W2888930363","https://openalex.org/W2889213362","https://openalex.org/W2892009249","https://openalex.org/W2912937645","https://openalex.org/W2936078256","https://openalex.org/W2936774411","https://openalex.org/W2951970475","https://openalex.org/W2962369866","https://openalex.org/W2962699523","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2963403868","https://openalex.org/W2963414781","https://openalex.org/W2963681135","https://openalex.org/W2963736842","https://openalex.org/W2963739817","https://openalex.org/W2964159205","https://openalex.org/W2972389417","https://openalex.org/W2972778435","https://openalex.org/W2972864786","https://openalex.org/W2972889948","https://openalex.org/W4385245566","https://openalex.org/W6601563604","https://openalex.org/W6640708543","https://openalex.org/W6676562027","https://openalex.org/W6735390525","https://openalex.org/W6736346607","https://openalex.org/W6739769129","https://openalex.org/W6739901393","https://openalex.org/W6742537141","https://openalex.org/W6747398299","https://openalex.org/W6753186555","https://openalex.org/W6754299077","https://openalex.org/W6758673196","https://openalex.org/W6760966419","https://openalex.org/W6764051988","https://openalex.org/W6765939562"],"related_works":["https://openalex.org/W2322874084","https://openalex.org/W4308856035","https://openalex.org/W4398186165","https://openalex.org/W2971748376","https://openalex.org/W3150250461","https://openalex.org/W2579205871","https://openalex.org/W4311657477","https://openalex.org/W2166510438","https://openalex.org/W2916847028","https://openalex.org/W3094813857"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,32,52,103],"novel":[4],"semi-supervised":[5,158],"end-to-end":[6,141],"automatic":[7],"speech":[8,172],"recognition":[9],"(ASR)":[10],"method":[11],"that":[12,35,86,156],"employs":[13],"consistency":[14,23,45,62,72,88,95,105,121,151,163],"training":[15,63,73,89,106,164],"with":[16,161],"the":[17,48,120,123,140,147],"use":[18],"of":[19,54,122],"unlabeled":[20,25,171],"data.":[21,173],"In":[22,42,98],"training,":[24],"data":[26],"can":[27,46,165],"be":[28],"utilized":[29],"for":[30],"constraining":[31],"model":[33,49],"such":[34],"it":[36],"becomes":[37],"invariant":[38],"to":[39,51,64,74,109,118],"small":[40],"deformation.":[41],"fact,":[43],"considering":[44],"make":[47],"robust":[50],"variety":[53],"input":[55],"examples.":[56],"While":[57],"previous":[58],"studies":[59,69],"have":[60,70],"applied":[61],"primitive":[65],"classification":[66],"problems,":[67],"no":[68],"employed":[71],"tackle":[75],"sequence-to-sequence":[76,111],"generation":[77,94,112,124],"problems":[78],"including":[79],"end-to-":[80],"end":[81],"ASR.":[82],"One":[83],"problem":[84],"is":[85,117],"existing":[87],"schemes":[90],"cannot":[91],"take":[92],"sequence-level":[93,104,162],"into":[96],"consideration.":[97],"this":[99],"paper,":[100],"we":[101,136],"propose":[102],"scheme":[107],"specialized":[108],"handle":[110],"problems.":[113],"Our":[114,153],"key":[115],"idea":[116],"consider":[119],"function":[125,149],"by":[126],"utilizing":[127],"beam":[128],"search":[129],"decoding":[130],"results.":[131],"For":[132],"semi-":[133],"supervised":[134],"learning,":[135],"adopt":[137],"Transformer":[138],"as":[139,146],"ASR":[142,168],"model,":[143],"and":[144],"SpecAugment":[145],"deformation":[148],"in":[150],"training.":[152],"experiments":[154],"show":[155],"our":[157],"learning":[159],"proposal":[160],"efficiently":[166],"improve":[167],"performance":[169],"using":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}