{"id":"https://openalex.org/W3007528493","doi":"https://doi.org/10.1109/asru46091.2019.9004027","title":"Attention Based On-Device Streaming Speech Recognition with Large Speech Corpus","display_name":"Attention Based On-Device Streaming Speech Recognition with Large Speech Corpus","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3007528493","doi":"https://doi.org/10.1109/asru46091.2019.9004027","mag":"3007528493"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9004027","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9004027","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/A5052377938","display_name":"Kwangyoun Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Kwangyoun Kim","raw_affiliation_strings":["Samsung Electronics Co., Ltd., Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics Co., Ltd., Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"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/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyungmin Lee","raw_affiliation_strings":["Samsung Electronics Co., Ltd., Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics Co., Ltd., Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113125574","display_name":"Dhananjaya Gowda","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dhananjaya Gowda","raw_affiliation_strings":["Samsung Electronics Co., Ltd., Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics Co., Ltd., Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029787807","display_name":"Jun\u2010Mo Park","orcid":"https://orcid.org/0000-0001-5997-0296"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Junmo Park","raw_affiliation_strings":["Samsung Electronics Co., Ltd., Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics Co., Ltd., Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100340036","display_name":"Sung-Soo Kim","orcid":"https://orcid.org/0000-0003-3207-4648"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungsoo Kim","raw_affiliation_strings":["Samsung Electronics Co., Ltd., Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics Co., Ltd., Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101747609","display_name":"Sichen Jin","orcid":"https://orcid.org/0000-0002-5591-7532"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sichen Jin","raw_affiliation_strings":["Samsung Electronics Co., Ltd., Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics Co., Ltd., Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090768657","display_name":"Young-Yoon Lee","orcid":"https://orcid.org/0000-0001-6117-5240"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Young-Yoon Lee","raw_affiliation_strings":["Samsung Electronics Co., Ltd., Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics Co., Ltd., Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041915512","display_name":"Jinsu Yeo","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jinsu Yeo","raw_affiliation_strings":["Samsung Electronics Co., Ltd., Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics Co., Ltd., Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374565","display_name":"Daehyun Kim","orcid":"https://orcid.org/0000-0001-9233-2747"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Daehyun Kim","raw_affiliation_strings":["Samsung Electronics Co., Ltd., Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics Co., Ltd., Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057180394","display_name":"Seokyeong Jung","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seokyeong Jung","raw_affiliation_strings":["Samsung Electronics Co., Ltd., Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics Co., Ltd., Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004902602","display_name":"Jungin Lee","orcid":"https://orcid.org/0000-0003-0390-119X"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jungin Lee","raw_affiliation_strings":["Samsung Electronics Co., Ltd., Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics Co., Ltd., Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085865703","display_name":"Myoungji Han","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Myoungji Han","raw_affiliation_strings":["Samsung Electronics Co., Ltd., Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics Co., Ltd., Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100684422","display_name":"Chanwoo Kim","orcid":"https://orcid.org/0000-0003-0193-8167"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chanwoo Kim","raw_affiliation_strings":["Samsung Electronics Co., Ltd., Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics Co., Ltd., Korea","institution_ids":["https://openalex.org/I2250650973"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":13,"corresponding_author_ids":["https://openalex.org/A5052377938"],"corresponding_institution_ids":["https://openalex.org/I2250650973"],"apc_list":null,"apc_paid":null,"fwci":7.0009,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.97555042,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"956","last_page":"963"},"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":0.9980000257492065,"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":0.8060727715492249},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7199915647506714},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.716197669506073},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4916706681251526},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4760681986808777},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.43893763422966003},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4293934106826782},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39902377128601074},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15780135989189148},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08580911159515381}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8060727715492249},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7199915647506714},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.716197669506073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4916706681251526},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4760681986808777},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.43893763422966003},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4293934106826782},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39902377128601074},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15780135989189148},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08580911159515381},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru46091.2019.9004027","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9004027","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":[{"display_name":"Peace, Justice and strong institutions","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1524333225","https://openalex.org/W1828163288","https://openalex.org/W1855892484","https://openalex.org/W2056738732","https://openalex.org/W2064675550","https://openalex.org/W2127141656","https://openalex.org/W2133564696","https://openalex.org/W2491408735","https://openalex.org/W2526425061","https://openalex.org/W2605141709","https://openalex.org/W2750499125","https://openalex.org/W2787998955","https://openalex.org/W2799800213","https://openalex.org/W2898997786","https://openalex.org/W2905263927","https://openalex.org/W2936774411","https://openalex.org/W2962728618","https://openalex.org/W2962784628","https://openalex.org/W2962824709","https://openalex.org/W2963240019","https://openalex.org/W2963414781","https://openalex.org/W2963747784","https://openalex.org/W2963827914","https://openalex.org/W2963920996","https://openalex.org/W2964272710","https://openalex.org/W2964308564","https://openalex.org/W2972816482","https://openalex.org/W3008587939","https://openalex.org/W4294619417","https://openalex.org/W6623517193","https://openalex.org/W6629052376","https://openalex.org/W6631362777","https://openalex.org/W6638749077","https://openalex.org/W6639156005","https://openalex.org/W6679434410","https://openalex.org/W6723310180","https://openalex.org/W6735706088","https://openalex.org/W6743440867","https://openalex.org/W6747158283","https://openalex.org/W6756165562","https://openalex.org/W6757856092"],"related_works":["https://openalex.org/W2019914509","https://openalex.org/W3101868899","https://openalex.org/W1937192591","https://openalex.org/W3080136773","https://openalex.org/W767271433","https://openalex.org/W2048917925","https://openalex.org/W1989705153","https://openalex.org/W4290682478","https://openalex.org/W2953291251","https://openalex.org/W2884483159"],"abstract_inverted_index":{"In":[0,66],"this":[1],"paper,":[2],"we":[3,68,117,127],"present":[4],"a":[5,32,130],"new":[6],"on-device":[7],"automatic":[8],"speech":[9],"recognition":[10,34,91],"(ASR)":[11],"system":[12],"based":[13],"on":[14,134],"monotonic":[15],"chunk-wise":[16],"attention":[17],"(MoChA)":[18],"models":[19,71,121],"trained":[20],"with":[21,99,122],"large":[22],"(>":[23],"10K":[24],"hours)":[25],"corpus.":[26],"We":[27],"attained":[28],"around":[29],"90%":[30],"of":[31,44],"word":[33,55,137],"rate":[35,57,139],"for":[36,141],"general":[37,146],"domain":[38],"mainly":[39],"by":[40,72],"using":[41,78],"joint":[42],"training":[43],"connectionist":[45],"temporal":[46],"classifier":[47],"(CTC)":[48],"and":[49,62,126],"cross":[50],"entropy":[51],"(CE)":[52],"losses,":[53],"minimum":[54],"error":[56,138],"(MWER)":[58],"training,":[59],"layer-wise":[60],"pretraining":[61],"data":[63],"augmentation":[64],"methods.":[65],"addition,":[67],"compressed":[69],"our":[70],"more":[73],"than":[74,111],"3.4":[75],"times":[76],"smaller":[77],"an":[79],"iterative":[80],"hyper":[81],"low-rank":[82],"approximation":[83],"(LRA)":[84],"method":[85],"while":[86],"minimizing":[87],"the":[88,105,119,145],"degradation":[89],"in":[90,136],"accuracy.":[92],"The":[93],"memory":[94],"footprint":[95],"was":[96],"further":[97],"reduced":[98],"8-bit":[100],"quantization":[101],"to":[102,109],"bring":[103],"down":[104],"final":[106],"model":[107],"size":[108],"lower":[110],"39":[112],"MB.":[113],"For":[114],"on-demand":[115],"adaptation,":[116],"fused":[118],"MoChA":[120],"statistical":[123],"n-gram":[124],"models,":[125],"could":[128],"achieve":[129],"relatively":[131],"36%":[132],"improvement":[133],"average":[135],"(WER)":[140],"target":[142],"domains":[143],"including":[144],"domain.":[147]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
