{"id":"https://openalex.org/W3008587939","doi":"https://doi.org/10.1109/asru46091.2019.9003976","title":"End-to-End Training of a Large Vocabulary End-to-End Speech Recognition System","display_name":"End-to-End Training of a Large Vocabulary End-to-End Speech Recognition System","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3008587939","doi":"https://doi.org/10.1109/asru46091.2019.9003976","mag":"3008587939"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9003976","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003976","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5100684422","display_name":"Chanwoo Kim","orcid":"https://orcid.org/0000-0003-0193-8167"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chanwoo Kim","raw_affiliation_strings":["Samsung Research"],"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101841393","display_name":"Sung-Soo Kim","orcid":"https://orcid.org/0009-0004-9441-0672"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sungsoo Kim","raw_affiliation_strings":["Samsung Research"],"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052377938","display_name":"Kwangyoun Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kwangyoun Kim","raw_affiliation_strings":["Samsung Research"],"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065995328","display_name":"Mehul Kumar","orcid":"https://orcid.org/0000-0001-7341-2362"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehul Kumar","raw_affiliation_strings":["Samsung Research"],"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396580","display_name":"Jiyeon Kim","orcid":"https://orcid.org/0000-0001-7964-5060"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiyeon Kim","raw_affiliation_strings":["Samsung Research"],"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100747693","display_name":"Kyungmin Lee","orcid":"https://orcid.org/0000-0003-1782-0729"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyungmin Lee","raw_affiliation_strings":["Samsung Research"],"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101194806","display_name":"Changwoo Han","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changwoo Han","raw_affiliation_strings":["Samsung Research"],"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043920881","display_name":"Abhinav Garg","orcid":"https://orcid.org/0000-0001-5082-5500"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhinav Garg","raw_affiliation_strings":["Samsung Research"],"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055878624","display_name":"Eunhyang Kim","orcid":"https://orcid.org/0000-0003-4720-9277"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eunhyang Kim","raw_affiliation_strings":["Samsung Research"],"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022480907","display_name":"Minkyoo Shin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minkyoo Shin","raw_affiliation_strings":["Samsung Research"],"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079810318","display_name":"Shatrughan Singh","orcid":"https://orcid.org/0000-0003-3758-3214"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shatrughan Singh","raw_affiliation_strings":["Samsung Research"],"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003679010","display_name":"Larry Heck","orcid":"https://orcid.org/0000-0003-3358-6362"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Larry Heck","raw_affiliation_strings":["Samsung Research"],"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113125574","display_name":"Dhananjaya Gowda","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhananjaya Gowda","raw_affiliation_strings":["Samsung Research"],"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":13,"corresponding_author_ids":["https://openalex.org/A5100684422"],"corresponding_institution_ids":["https://openalex.org/I4210101778"],"apc_list":null,"apc_paid":null,"fwci":4.4805,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.95732625,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"562","last_page":"569"},"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":0.9986000061035156,"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":0.996399998664856,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.9438430070877075},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7364677786827087},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6417815685272217},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5784035325050354},{"id":"https://openalex.org/keywords/end-user","display_name":"End user","score":0.48271510004997253},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4468367099761963},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35513055324554443},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10943475365638733},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10219311714172363}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.9438430070877075},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7364677786827087},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6417815685272217},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5784035325050354},{"id":"https://openalex.org/C91262260","wikidata":"https://www.wikidata.org/wiki/Q528074","display_name":"End user","level":2,"score":0.48271510004997253},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4468367099761963},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35513055324554443},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10943475365638733},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10219311714172363},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru46091.2019.9003976","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003976","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W587794757","https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1566425957","https://openalex.org/W1607274768","https://openalex.org/W1616590059","https://openalex.org/W1815076433","https://openalex.org/W1915251500","https://openalex.org/W1979651826","https://openalex.org/W2062164080","https://openalex.org/W2063656732","https://openalex.org/W2064675550","https://openalex.org/W2088489891","https://openalex.org/W2099621636","https://openalex.org/W2103681028","https://openalex.org/W2107508685","https://openalex.org/W2114719288","https://openalex.org/W2136439176","https://openalex.org/W2160815625","https://openalex.org/W2191779130","https://openalex.org/W2213952365","https://openalex.org/W2326699523","https://openalex.org/W2327501763","https://openalex.org/W2396889049","https://openalex.org/W2398042854","https://openalex.org/W2400339399","https://openalex.org/W2400570867","https://openalex.org/W2402144811","https://openalex.org/W2515737026","https://openalex.org/W2517616541","https://openalex.org/W2545177271","https://openalex.org/W2589857635","https://openalex.org/W2617258110","https://openalex.org/W2622203030","https://openalex.org/W2622263826","https://openalex.org/W2702006285","https://openalex.org/W2748584437","https://openalex.org/W2750499125","https://openalex.org/W2785572076","https://openalex.org/W2787998955","https://openalex.org/W2799800213","https://openalex.org/W2803023894","https://openalex.org/W2936774411","https://openalex.org/W2944255943","https://openalex.org/W2953384591","https://openalex.org/W2962728618","https://openalex.org/W2962824709","https://openalex.org/W2963122170","https://openalex.org/W2963362078","https://openalex.org/W2963403868","https://openalex.org/W2963747784","https://openalex.org/W2963980003","https://openalex.org/W2964138484","https://openalex.org/W2964272710","https://openalex.org/W2972426539","https://openalex.org/W2972816482","https://openalex.org/W2997454826","https://openalex.org/W3007185811","https://openalex.org/W3007528493","https://openalex.org/W3103005696","https://openalex.org/W4294619417","https://openalex.org/W4301239768","https://openalex.org/W4385245566","https://openalex.org/W6617368339","https://openalex.org/W6623517193","https://openalex.org/W6638545294","https://openalex.org/W6675409298","https://openalex.org/W6687152286","https://openalex.org/W6688428952","https://openalex.org/W6713134421","https://openalex.org/W6739901393","https://openalex.org/W6747158283"],"related_works":["https://openalex.org/W4299590256","https://openalex.org/W2151749779","https://openalex.org/W3163634122","https://openalex.org/W2110442089","https://openalex.org/W3119482857","https://openalex.org/W2919182614","https://openalex.org/W2166381389","https://openalex.org/W4393280045","https://openalex.org/W2054736184","https://openalex.org/W3159728998"],"abstract_inverted_index":{"In":[0],"this":[1,112],"paper,":[2],"we":[3,146,182],"present":[4],"an":[5,56,166],"end-to-end":[6,12,106,159],"training":[7,17,113],"framework":[8],"for":[9,60,178],"building":[10],"state-of-the-art":[11],"speech":[13,107,180],"recognition":[14,108],"systems.":[15],"Our":[16,105],"system":[18,91,109],"utilizes":[19],"a":[20,116,132,148,154,184],"cluster":[21],"of":[22,89,122,150,186],"Central":[23],"Processing":[24,29],"Units":[25,30],"(CPUs)":[26],"and":[27,55,66,98],"Graphics":[28],"(GPUs).":[31],"The":[32,63,74],"entire":[33],"data":[34,38,61],"reading,":[35],"large":[36],"scale":[37],"augmentation,":[39],"neural":[40,82],"network":[41,83],"parameter":[42],"updates":[43],"are":[44,68],"all":[45],"performed":[46],"\u201con-the-fly\u201d.":[47],"We":[48,85],"use":[49],"vocal":[50],"tract":[51],"length":[52],"perturbation":[53],"[1]":[54],"acoustic":[57],"simulator":[58],"[2]":[59],"augmentation.":[62],"processed":[64],"features":[65],"labels":[67],"sent":[69],"to":[70,80],"the":[71,87,93,99,123,138,169,190],"GPU":[72],"cluster.":[73],"Horovod":[75],"allreduce":[76],"approach":[77,175],"is":[78,176],"employed":[79,177],"train":[81],"parameters.":[84],"evaluated":[86],"effectiveness":[88],"our":[90],"on":[92,120,189],"standard":[94],"Librispeech":[95],"corpus":[96],"[3]":[97],"10,000-hr":[100],"anonymized":[101],"Bixby":[102,141,192],"English":[103,140],"dataset.":[104],"built":[110],"using":[111,153],"infrastructure":[114],"showed":[115],"2.44":[117],"%":[118,152,188],"WER":[119,149,185],"test-clean":[121],"LibriSpeech":[124],"test":[125,144,195],"set":[126],"after":[127,161],"applying":[128,162],"shallow":[129,163],"fusion":[130,164],"with":[131,165],"Transformer":[133],"language":[134],"model":[135,160],"(LM).":[136],"For":[137],"proprietary":[139],"open":[142,193],"domain":[143,194],"set,":[145],"obtained":[147,183],"7.92":[151],"Bidirectional":[155],"Full":[156],"Attention":[157],"(BFA)":[158],"RNN-LM.":[167],"When":[168],"monotonic":[170],"chunckwise":[171],"attention":[172],"(MoCha)":[173],"based":[174],"streaming":[179],"recognition,":[181],"9.95":[187],"same":[191],"set.":[196]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}