{"id":"https://openalex.org/W2914172742","doi":"https://doi.org/10.1109/slt.2018.8639662","title":"On-Device End-to-end Speech Recognition with Multi-Step Parallel Rnns","display_name":"On-Device End-to-end Speech Recognition with Multi-Step Parallel Rnns","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2914172742","doi":"https://doi.org/10.1109/slt.2018.8639662","mag":"2914172742"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639662","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639662","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":"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/A5011500561","display_name":"Yoonho Boo","orcid":"https://orcid.org/0000-0002-6656-4445"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yoonho Boo","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University, Seoul, 08826, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, 08826, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108758586","display_name":"Jin-Hwan Park","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jinhwan Park","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University, Seoul, 08826, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, 08826, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065076995","display_name":"Lukas Jyuhn\u2010Hsiarn Lee","orcid":"https://orcid.org/0000-0003-1095-6877"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Lukas Lee","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University, Seoul, 08826, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, 08826, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113491293","display_name":"Wonyong Sung","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wonyong Sung","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University, Seoul, 08826, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, 08826, Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19079277,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"376","last_page":"381"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9883999824523926,"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/T10320","display_name":"Neural Networks and Applications","score":0.9879999756813049,"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/recurrent-neural-network","display_name":"Recurrent neural network","score":0.8635296821594238},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.842861533164978},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6774946451187134},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6636942625045776},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.6079689264297485},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5952085852622986},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"Long short term memory","score":0.565584659576416},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.5545536279678345},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5245473980903625},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4809683859348297},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4786592423915863},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.42103493213653564},{"id":"https://openalex.org/keywords/auxiliary-memory","display_name":"Auxiliary memory","score":0.414226233959198},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3557995855808258},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.299626886844635},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29818853735923767},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.29719996452331543},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15951892733573914},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09397965669631958}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.8635296821594238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.842861533164978},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6774946451187134},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6636942625045776},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.6079689264297485},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5952085852622986},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.565584659576416},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.5545536279678345},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5245473980903625},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4809683859348297},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4786592423915863},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.42103493213653564},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.414226233959198},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3557995855808258},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.299626886844635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29818853735923767},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.29719996452331543},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15951892733573914},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09397965669631958},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2018.8639662","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639662","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":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320315121","display_name":"Samsung Advanced Institute of Technology","ror":null},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1582482241","https://openalex.org/W1600744878","https://openalex.org/W1710082047","https://openalex.org/W1999085092","https://openalex.org/W2024490156","https://openalex.org/W2046932483","https://openalex.org/W2082703217","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2293829681","https://openalex.org/W2312434537","https://openalex.org/W2545177271","https://openalex.org/W2553397501","https://openalex.org/W2751185861","https://openalex.org/W2765920929","https://openalex.org/W2950297649","https://openalex.org/W2952436057","https://openalex.org/W2962735857","https://openalex.org/W2963211739","https://openalex.org/W2963953073","https://openalex.org/W2963979492","https://openalex.org/W6631362777","https://openalex.org/W6675365184","https://openalex.org/W6691800262","https://openalex.org/W6734588641","https://openalex.org/W6743638068","https://openalex.org/W6745640171","https://openalex.org/W6755651582","https://openalex.org/W6764398373"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1761388607","https://openalex.org/W1997922073","https://openalex.org/W2604685715","https://openalex.org/W2412160900","https://openalex.org/W2136453575","https://openalex.org/W1596913645","https://openalex.org/W3115527998","https://openalex.org/W4360103953"],"abstract_inverted_index":{"Most":[0],"of":[1,28,50,95,109,146],"the":[2,14,26,48,55,107,117,124],"current":[3],"automatic":[4],"speech":[5,17,36],"recognition":[6,18,30,37],"is":[7,22,114,126],"performed":[8],"on":[9,19,74,142],"a":[10,101,143],"remote":[11],"server.":[12],"However,":[13],"demand":[15],"for":[16,105],"personal":[20],"devices":[21],"increasing,":[23],"owing":[24],"to":[25],"requirement":[27],"shorter":[29],"latency":[31],"and":[32,99,123],"increased":[33],"privacy.":[34],"End-to-end":[35],"that":[38],"employs":[39],"recurrent":[40,62,92],"neural":[41],"networks":[42],"(RNNs)":[43],"shows":[44],"good":[45],"accuracy,":[46],"but":[47],"execution":[49,73],"conventional":[51],"RNNs,":[52],"such":[53],"as":[54],"long":[56],"short-term":[57],"memory":[58,67],"(LSTM)":[59],"or":[60,76,97],"gated":[61],"unit":[63],"(GRU),":[64],"demands":[65],"many":[66],"accesses,":[68],"thus":[69],"hindering":[70],"its":[71],"real-time":[72,138],"smart-phones":[75],"embedded":[77],"systems.":[78],"To":[79],"solve":[80],"this":[81],"problem,":[82],"we":[83],"built":[84],"an":[85,147],"end-to-end":[86],"acoustic":[87],"model":[88],"(AM)":[89],"using":[90,128],"linear":[91],"units":[93],"instead":[94],"LSTM":[96],"GRU":[98],"employed":[100],"multi-step":[102],"parallel":[103],"approach":[104],"reducing":[106],"number":[108],"DRAM":[110],"accesses.":[111],"The":[112,133],"AM":[113],"trained":[115],"with":[116],"connectionist":[118],"temporal":[119],"classification":[120],"(CTC)":[121],"loss,":[122],"decoding":[125],"conducted":[127],"weighted":[129],"finite-state":[130],"transducers":[131],"(WFSTs).":[132],"proposed":[134],"system":[135],"achieves":[136],"x4.8":[137],"speed":[139],"when":[140],"executed":[141],"single":[144],"core":[145],"ARM":[148],"CPU-based":[149],"system.":[150]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}