{"id":"https://openalex.org/W3011877917","doi":"https://doi.org/10.1109/sips47522.2019.9020317","title":"Exploration of On-device End-to-End Acoustic Modeling with Neural Networks","display_name":"Exploration of On-device End-to-End Acoustic Modeling with Neural Networks","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W3011877917","doi":"https://doi.org/10.1109/sips47522.2019.9020317","mag":"3011877917"},"language":"en","primary_location":{"id":"doi:10.1109/sips47522.2019.9020317","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sips47522.2019.9020317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Workshop on Signal Processing Systems (SiPS)","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/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":true,"raw_author_name":"Wonyong Sung","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, 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, Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","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, Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5113491293"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.1443,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61970633,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"160","last_page":"165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987999796867371,"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/T10860","display_name":"Speech and Audio Processing","score":0.9968000054359436,"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":0.8657503128051758},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.7846134901046753},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7807039618492126},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.6003727912902832},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5912153720855713},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5290849208831787},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.4963863492012024},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4913395941257477},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4459965229034424},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3517923951148987},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.347939670085907},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3356670141220093},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31534361839294434},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.287677526473999}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8657503128051758},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.7846134901046753},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7807039618492126},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.6003727912902832},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5912153720855713},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5290849208831787},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.4963863492012024},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4913395941257477},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4459965229034424},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3517923951148987},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.347939670085907},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3356670141220093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31534361839294434},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.287677526473999},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/sips47522.2019.9020317","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sips47522.2019.9020317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Workshop on Signal Processing Systems (SiPS)","raw_type":"proceedings-article"},{"id":"pmh:oai:s-space.snu.ac.kr:10371/186942","is_oa":false,"landing_page_url":"https://hdl.handle.net/10371/186942","pdf_url":null,"source":{"id":"https://openalex.org/S4306401345","display_name":"Seoul National University Open Repository (Seoul National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139264467","host_organization_name":"Seoul National University","host_organization_lineage":["https://openalex.org/I139264467"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1600744878","https://openalex.org/W1815076433","https://openalex.org/W1836465849","https://openalex.org/W2024490156","https://openalex.org/W2064675550","https://openalex.org/W2107878631","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2193413348","https://openalex.org/W2194775991","https://openalex.org/W2212703438","https://openalex.org/W2263232528","https://openalex.org/W2312434537","https://openalex.org/W2519091744","https://openalex.org/W2567070169","https://openalex.org/W2613904329","https://openalex.org/W2754232744","https://openalex.org/W2786951478","https://openalex.org/W2787110826","https://openalex.org/W2791366550","https://openalex.org/W2799549586","https://openalex.org/W2892090442","https://openalex.org/W2950297649","https://openalex.org/W2952436057","https://openalex.org/W2963022149","https://openalex.org/W2963174729","https://openalex.org/W2963211739","https://openalex.org/W2963513932","https://openalex.org/W2964199361","https://openalex.org/W2964347220","https://openalex.org/W2972630480","https://openalex.org/W4254816979","https://openalex.org/W4297687616","https://openalex.org/W4297689207","https://openalex.org/W4297818305","https://openalex.org/W4301368689","https://openalex.org/W6631190155","https://openalex.org/W6638545294","https://openalex.org/W6638667902","https://openalex.org/W6687566353","https://openalex.org/W6688167117","https://openalex.org/W6691800262","https://openalex.org/W6729053843","https://openalex.org/W6731370813","https://openalex.org/W6736780897","https://openalex.org/W6737778391","https://openalex.org/W6744720862","https://openalex.org/W6747270024","https://openalex.org/W6754450847","https://openalex.org/W6754522980","https://openalex.org/W6764398373"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1761388607","https://openalex.org/W3120961607","https://openalex.org/W1997922073","https://openalex.org/W4401568740","https://openalex.org/W2916997151","https://openalex.org/W2495256954","https://openalex.org/W2259317772","https://openalex.org/W2949174760"],"abstract_inverted_index":{"Real-time":[0],"speech":[1,22,172],"recognition":[2,23,173],"on":[3,85,174],"mobile":[4],"and":[5,24,126,146,158],"embedded":[6,51,86,206],"devices":[7,52],"is":[8,17,25,46],"an":[9,43],"important":[10],"application":[11],"of":[12,21,42,62,93,143],"neural":[13,34,133],"networks.":[14],"Acoustic":[15],"modeling":[16,77],"the":[18,38,54,65,91,109,114,120,166,182],"fundamental":[19],"part":[20],"usually":[26],"implemented":[27],"with":[28],"long":[29],"short-term":[30],"memory":[31,94],"(LSTM)-based":[32],"recurrent":[33],"networks":[35,134],"(RNNs).":[36],"However,":[37],"single":[39],"thread":[40],"execution":[41,183],"LSTM":[44,194],"RNN":[45],"extremely":[47],"slow":[48],"in":[49,156],"most":[50],"because":[53],"algorithm":[55],"needs":[56],"to":[57,193,205,211],"fetch":[58],"a":[59,74,105,151,188],"large":[60,153],"number":[61],"parameters":[63,110],"from":[64,113],"DRAM":[66],"for":[67],"computing":[68],"each":[69,141],"output":[70,102],"sample.":[71],"We":[72,177],"explore":[73,132],"few":[75],"acoustic":[76],"algorithms":[78,89,117],"that":[79,99,135],"can":[80,149,200],"be":[81,201],"executed":[82],"very":[83,152],"efficiently":[84],"devices.":[87],"These":[88],"reduce":[90],"overhead":[92],"accesses":[95],"using":[96,165],"multi-timestep":[97],"parallelization":[98],"computes":[100],"multiple":[101],"samples":[103],"at":[104,140],"time":[106],"by":[107,147],"reading":[108],"only":[111,179,204],"once":[112],"DRAM.":[115],"The":[116,161],"considered":[118],"are":[119],"quasi":[121],"RNNs":[122],"(QRNNs),":[123],"Gated":[124,159],"ConvNets,":[125],"diagonalized":[127],"LSTMs.":[128],"In":[129],"addition,":[130],"we":[131],"equip":[136],"one-dimensional":[137],"(1-D)":[138],"convolution":[139],"layer":[142],"these":[144],"algorithms,":[145],"which":[148],"obtain":[150,187],"performance":[154],"increase":[155,181],"QRNNs":[157],"ConvNets.":[160],"experiments":[162],"were":[163],"conducted":[164],"connectionist":[167],"temporal":[168],"classification":[169],"(CTC)-based":[170],"end-to-end":[171],"WSJ":[175],"corpus.":[176],"not":[178,203],"significantly":[180],"speed":[184],"but":[185,209],"also":[186,210],"much":[189],"higher":[190],"accuracy,":[191],"compared":[192],"RNN-based":[195],"modeling.":[196],"Thus,":[197],"this":[198],"work":[199],"applicable":[202],"system-based":[207],"implementations":[208],"server-based":[212],"ones.":[213]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}