{"id":"https://openalex.org/W2883586237","doi":"https://doi.org/10.1109/slt.2018.8639619","title":"Back-Translation-Style Data Augmentation for end-to-end ASR","display_name":"Back-Translation-Style Data Augmentation for end-to-end ASR","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2883586237","doi":"https://doi.org/10.1109/slt.2018.8639619","mag":"2883586237"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639619","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","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/A5078778981","display_name":"Tomoki Hayashi","orcid":"https://orcid.org/0000-0001-8782-4093"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Tomoki Hayashi","raw_affiliation_strings":["Nagoya University, Nagoya, JAPAN"],"affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, JAPAN","institution_ids":["https://openalex.org/I60134161"]}]},{"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":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433533","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0002-3250-4284"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Google, Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University, Nagoya, JAPAN"],"affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, JAPAN","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087554069","display_name":"Takaaki Hori","orcid":"https://orcid.org/0000-0003-4560-8039"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takaaki Hori","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge MA, USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003156858","display_name":"Ram\u00f3n Fern\u00e1ndez Astudillo","orcid":"https://orcid.org/0000-0001-9443-2346"},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Ramon Astudillo","raw_affiliation_strings":["Spoken Language Systems Lab, INESC-ID Lisboa, Portugal"],"affiliations":[{"raw_affiliation_string":"Spoken Language Systems Lab, INESC-ID Lisboa, Portugal","institution_ids":["https://openalex.org/I121345201"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042118446","display_name":"Kazuya Takeda","orcid":"https://orcid.org/0000-0002-0330-1787"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuya Takeda","raw_affiliation_strings":["Nagoya University, Nagoya, JAPAN"],"affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, JAPAN","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5078778981"],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":9.1215,"has_fulltext":false,"cited_by_count":96,"citation_normalized_percentile":{"value":0.98237432,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"426","last_page":"433"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/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/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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":0.8036496043205261},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7495050430297852},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6881858706474304},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6003851294517517},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.541074275970459},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5053856372833252},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4959336221218109},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43218672275543213},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36611974239349365}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8036496043205261},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7495050430297852},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6881858706474304},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6003851294517517},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.541074275970459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5053856372833252},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4959336221218109},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43218672275543213},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36611974239349365},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2018.8639619","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1586532344","https://openalex.org/W1902237438","https://openalex.org/W1915251500","https://openalex.org/W1990005915","https://openalex.org/W2095705004","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2150355110","https://openalex.org/W2157331557","https://openalex.org/W2193413348","https://openalex.org/W2293634267","https://openalex.org/W2409027918","https://openalex.org/W2545177271","https://openalex.org/W2577366047","https://openalex.org/W2627092829","https://openalex.org/W2808706139","https://openalex.org/W2888779557","https://openalex.org/W2962699523","https://openalex.org/W2962780374","https://openalex.org/W2963216553","https://openalex.org/W2963432880","https://openalex.org/W2963602293","https://openalex.org/W2963816901","https://openalex.org/W2964012862","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2964308564","https://openalex.org/W4293714597","https://openalex.org/W4298393544","https://openalex.org/W6600284362","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6635078382","https://openalex.org/W6640059789","https://openalex.org/W6674330103","https://openalex.org/W6675365184","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6687566353","https://openalex.org/W6695909211","https://openalex.org/W6696934422","https://openalex.org/W6714142977","https://openalex.org/W6728910023","https://openalex.org/W6732447497","https://openalex.org/W6739366949","https://openalex.org/W6743477263","https://openalex.org/W6745388339","https://openalex.org/W6746700228","https://openalex.org/W6752888775"],"related_works":["https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W3011059803","https://openalex.org/W1999612375","https://openalex.org/W2938107654","https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W3151736118","https://openalex.org/W4404782863"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,42],"propose":[4],"a":[5,18,44,50,57,62,71,121],"novel":[6],"data":[7],"augmentation":[8],"method":[9,150],"for":[10,166],"attention-based":[11],"end-to-end":[12],"automatic":[13],"speech":[14,28],"recognition":[15],"(E2E-ASR),":[16],"utilizing":[17],"large":[19,122],"amount":[20,123],"of":[21,39,52,64,74,98,124,153,160],"text":[22],"which":[23,48],"is":[24,78,130],"not":[25],"paired":[26,167],"with":[27],"signals.":[29],"Inspired":[30],"by":[31,56],"the":[32,37,96,99,113,117,133,158,164],"back-translation":[33],"technique":[34],"proposed":[35,149],"in":[36,92],"field":[38],"machine":[40],"translation,":[41],"build":[43],"neural":[45],"text-to-encoder":[46,114],"model":[47,105,115],"predicts":[49],"sequence":[51,63],"hidden":[53,68,100,118,135],"states":[54,69,101,119,136],"extracted":[55],"pre-trained":[58],"E2E-ASR":[59,93,128],"encoder":[60],"from":[61,120],"characters.":[65],"By":[66],"using":[67,132,143],"as":[70,137],"target":[72],"instead":[73],"acoustic":[75,109],"features,":[76],"it":[77],"possible":[79],"to":[80,90,104],"achieve":[81],"faster":[82],"attention":[83],"learning":[84],"and":[85,156],"reduce":[86],"computational":[87],"cost,":[88],"thanks":[89],"sub-sampling":[91],"encoder,":[94],"also":[95],"use":[97],"can":[102],"avoid":[103],"speaker":[106],"dependencies":[107],"unlike":[108],"features.":[110],"After":[111],"training,":[112],"generates":[116],"unpaired":[125],"text,":[126],"then":[127],"decoder":[129],"retrained":[131],"generated":[134],"additional":[138],"training":[139],"data.":[140,168],"Experimental":[141],"evaluation":[142],"LibriSpeech":[144],"dataset":[145],"demonstrates":[146],"that":[147],"our":[148],"achieves":[151],"improvement":[152],"ASR":[154],"performance":[155],"reduces":[157],"number":[159],"unknown":[161],"words":[162],"without":[163],"need":[165]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":19}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}