{"id":"https://openalex.org/W3015281123","doi":"https://doi.org/10.1109/icassp40776.2020.9053054","title":"Low-Latency Lightweight Streaming Speech Recognition with 8-Bit Quantized Simple Gated Convolutional Neural Networks","display_name":"Low-Latency Lightweight Streaming Speech Recognition with 8-Bit Quantized Simple Gated Convolutional Neural Networks","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015281123","doi":"https://doi.org/10.1109/icassp40776.2020.9053054","mag":"3015281123"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053054","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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":true,"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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101345581","display_name":"Xue Qian","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":"Xue Qian","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/A5103198267","display_name":"Youngmin Jo","orcid":"https://orcid.org/0000-0003-3473-7695"},"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":"Youngmin Jo","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/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, 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":4,"corresponding_author_ids":["https://openalex.org/A5108758586"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.3977,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.67307052,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1803","last_page":"1807"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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":0.9991000294685364,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9805999994277954,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.8714280128479004},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6365563273429871},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.6082302927970886},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5451527833938599},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5115288496017456},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.49823689460754395},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.46870917081832886},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45455044507980347},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4434250593185425},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.43332988023757935},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.43105530738830566},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.28472068905830383},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.27447444200515747},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23376819491386414},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1798863708972931},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08927261829376221}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8714280128479004},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6365563273429871},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.6082302927970886},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5451527833938599},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5115288496017456},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.49823689460754395},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.46870917081832886},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45455044507980347},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4434250593185425},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.43332988023757935},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.43105530738830566},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.28472068905830383},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.27447444200515747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23376819491386414},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1798863708972931},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08927261829376221},{"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/icassp40776.2020.9053054","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2024490156","https://openalex.org/W2064675550","https://openalex.org/W2127141656","https://openalex.org/W2193413348","https://openalex.org/W2553397501","https://openalex.org/W2567070169","https://openalex.org/W2613904329","https://openalex.org/W2781384251","https://openalex.org/W2891160178","https://openalex.org/W2892090442","https://openalex.org/W2944255943","https://openalex.org/W2952436057","https://openalex.org/W2962760690","https://openalex.org/W2962824709","https://openalex.org/W2963122961","https://openalex.org/W2963970792","https://openalex.org/W2964121744","https://openalex.org/W2964199361","https://openalex.org/W2964265128","https://openalex.org/W2972630480","https://openalex.org/W2973215447","https://openalex.org/W3008801297","https://openalex.org/W3103005696","https://openalex.org/W4297818305","https://openalex.org/W6631190155","https://openalex.org/W6687566353","https://openalex.org/W6731370813","https://openalex.org/W6737778391","https://openalex.org/W6747270024","https://openalex.org/W6754522980","https://openalex.org/W6754883025","https://openalex.org/W6764398373"],"related_works":["https://openalex.org/W2152099439","https://openalex.org/W1984163603","https://openalex.org/W3130422087","https://openalex.org/W2928062709","https://openalex.org/W4386302689","https://openalex.org/W2068996722","https://openalex.org/W3193699965","https://openalex.org/W4319917399","https://openalex.org/W3035490917","https://openalex.org/W4200309432"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,62],"recognition":[2,63,77,112],"(ASR)":[3],"is":[4,48,86,97],"very":[5],"important":[6],"for":[7,51,88],"mobile":[8,29],"devices.":[9],"However,":[10],"deep":[11],"neural":[12],"network-based":[13],"ASR":[14,47],"demands":[15],"a":[16,59,66,75,128],"large":[17],"number":[18],"of":[19,28,124],"computations,":[20],"while":[21],"the":[22,49,101,114,121],"memory":[23,102,137],"bandwidth":[24],"and":[25,104,118],"battery":[26],"capacity":[27],"devices":[30],"are":[31,35],"limited.":[32],"Server-based":[33],"implementations":[34],"mostly":[36],"employed,":[37],"but":[38],"this":[39,55],"increases":[40],"latency":[41,116],"or":[42],"privacy":[43],"concerns.":[44],"Efficient":[45],"on-device":[46,61],"solution":[50],"these":[52],"issues.":[53],"In":[54,83],"paper,":[56],"we":[57],"propose":[58],"low-latency":[60],"system":[64,109,134],"with":[65,80,120,145],"simple":[67],"gated":[68],"convolutional":[69],"network":[70],"(SGCN).":[71],"The":[72,107,133],"SGCN":[73,85],"shows":[74,139],"competitive":[76],"accuracy":[78],"even":[79],"1M":[81],"parameters.":[82],"addition,":[84],"advantageous":[87],"parallelization":[89],"which":[90],"enables":[91],"efficient":[92],"cache":[93],"utilization.":[94],"8-bit":[95],"quantization":[96],"applied":[98],"to":[99],"reduce":[100],"size":[103],"computation":[105],"time.":[106],"proposed":[108],"features":[110],"online":[111],"fulfilling":[113],"0.4s":[115],"limit":[117],"operates":[119],"real-time":[122],"factor":[123],"0.2":[125],"using":[126],"only":[127],"single":[129],"900MHz":[130],"CPU":[131],"core.":[132],"occupying":[135],"1.2MB":[136],"footprint":[138],"19.75%":[140],"word":[141],"error":[142],"rate":[143],"(WER)":[144],"greedy":[146],"decoding.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}