{"id":"https://openalex.org/W2886180730","doi":"https://doi.org/10.1109/slt.2018.8639693","title":"End-to-end Speech Recognition With Word-Based Rnn Language Models","display_name":"End-to-end Speech Recognition With Word-Based Rnn Language Models","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2886180730","doi":"https://doi.org/10.1109/slt.2018.8639693","mag":"2886180730"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639693","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/A5087554069","display_name":"Takaaki Hori","orcid":"https://orcid.org/0000-0003-4560-8039"},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takaaki Hori","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL)","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059500729","display_name":"Jaejin Cho","orcid":"https://orcid.org/0000-0001-5672-6765"},"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":"Jaejin Cho","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5087554069"],"corresponding_institution_ids":["https://openalex.org/I4210133125"],"apc_list":null,"apc_paid":null,"fwci":12.6954,"has_fulltext":false,"cited_by_count":124,"citation_normalized_percentile":{"value":0.98817127,"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":"389","last_page":"396"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9984999895095825,"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/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/computer-science","display_name":"Computer science","score":0.7919323444366455},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7098192572593689},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7040949463844299},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6735820174217224},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6050297021865845},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5745379328727722},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5476221442222595},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.543631374835968},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5104600191116333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46576476097106934},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.41602906584739685},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.13729235529899597},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1317480206489563},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07802513241767883}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7919323444366455},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7098192572593689},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7040949463844299},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6735820174217224},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6050297021865845},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5745379328727722},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5476221442222595},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.543631374835968},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5104600191116333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46576476097106934},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.41602906584739685},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.13729235529899597},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1317480206489563},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07802513241767883},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2018.8639693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639693","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.44999998807907104},{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W46679369","https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1501633760","https://openalex.org/W1524333225","https://openalex.org/W1600744878","https://openalex.org/W1686810756","https://openalex.org/W1815076433","https://openalex.org/W1915251500","https://openalex.org/W2046932483","https://openalex.org/W2102113734","https://openalex.org/W2118204484","https://openalex.org/W2143612262","https://openalex.org/W2144499799","https://openalex.org/W2408623794","https://openalex.org/W2525778437","https://openalex.org/W2526425061","https://openalex.org/W2530876040","https://openalex.org/W2545177271","https://openalex.org/W2577366047","https://openalex.org/W2597757402","https://openalex.org/W2627092829","https://openalex.org/W2739883972","https://openalex.org/W2761434131","https://openalex.org/W2787663903","https://openalex.org/W2799800213","https://openalex.org/W2962780374","https://openalex.org/W2962826786","https://openalex.org/W2963211739","https://openalex.org/W2963240019","https://openalex.org/W2963414781","https://openalex.org/W2963483399","https://openalex.org/W6600284362","https://openalex.org/W6601894380","https://openalex.org/W6623517193","https://openalex.org/W6631362777","https://openalex.org/W6635768407","https://openalex.org/W6637373629","https://openalex.org/W6638545294","https://openalex.org/W6640059789","https://openalex.org/W6675365184","https://openalex.org/W6681794868","https://openalex.org/W6728030952","https://openalex.org/W6728892627","https://openalex.org/W6728910023","https://openalex.org/W6732447497","https://openalex.org/W6735390525","https://openalex.org/W6746574493"],"related_works":["https://openalex.org/W2916997151","https://openalex.org/W2495256954","https://openalex.org/W50892825","https://openalex.org/W2259317772","https://openalex.org/W2949174760","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W4290708361"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,12,51,70,93,108,119,124,127,142,149,161,168],"impact":[4],"of":[5,14,107,126],"word-based":[6,34,84,94,128],"RNN":[7],"language":[8],"models":[9],"(RNN-LMs)":[10],"on":[11,176],"performance":[13],"end-to-end":[15,173],"automatic":[16],"speech":[17],"recognition":[18],"(ASR).":[19],"In":[20,76],"our":[21],"prior":[22,143],"work,":[23],"we":[24,79,139,146],"have":[25],"proposed":[26,150],"a":[27,82,131],"multi-level":[28,44,120],"LM,":[29,95,110],"in":[30,38,50,135,141],"which":[31,68,86,166],"character-based":[32,109],"and":[33,64,73],"RNN-LMs":[35,129],"are":[36],"combined":[37],"hybrid":[39],"CTC/attention-based":[40],"ASR.":[41],"Although":[42],"this":[43,77,177],"approach":[45],"achieves":[46,152],"significant":[47],"error":[48],"reduction":[49],"Wall":[52],"Street":[53],"Journal":[54],"(WSJ)":[55],"task,":[56],"two":[57],"different":[58],"LMs":[59],"need":[60],"to":[61,89,102,118,137],"be":[62],"trained":[63],"used":[65,140],"for":[66,155,172],"decoding,":[67],"increase":[69],"computational":[71],"cost":[72],"memory":[74],"usage.":[75],"paper,":[78],"further":[80],"propose":[81],"novel":[83],"RNN-LM,":[85],"allows":[87],"us":[88],"decode":[90],"with":[91,114],"only":[92],"where":[96],"it":[97],"provides":[98],"look-ahead":[99],"word":[100],"probabilities":[101],"predict":[103],"next":[104],"characters":[105],"instead":[106],"leading":[111],"competitive":[112],"accuracy":[113],"less":[115],"computation":[116],"compared":[117],"LM.":[121],"We":[122],"demonstrate":[123],"efficacy":[125],"using":[130],"larger":[132],"corpus,":[133],"LibriSpeech,":[134],"addition":[136],"WSJ":[138,156],"work.":[144],"Furthermore,":[145],"show":[147],"that":[148],"model":[151],"5.1":[153],"%WER":[154],"Eval'92":[157],"test":[158],"set":[159],"when":[160],"vocabulary":[162],"size":[163],"is":[164,167],"increased,":[165],"best":[169],"WER":[170],"reported":[171],"ASR":[174],"systems":[175],"benchmark.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":25},{"year":2019,"cited_by_count":28}],"updated_date":"2026-05-08T15:41:06.802602","created_date":"2025-10-10T00:00:00"}