{"id":"https://openalex.org/W2788770315","doi":"https://doi.org/10.1109/icassp.2018.8462127","title":"Limiting Numerical Precision of Neural Networks to Achieve Real-Time Voice Activity Detection","display_name":"Limiting Numerical Precision of Neural Networks to Achieve Real-Time Voice Activity Detection","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2788770315","doi":"https://doi.org/10.1109/icassp.2018.8462127","mag":"2788770315"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462127","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5063908850","display_name":"Jong Hwan Ko","orcid":"https://orcid.org/0000-0003-4434-4318"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jong Hwan Ko","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011623194","display_name":"Josh Fromm","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Josh Fromm","raw_affiliation_strings":["Department of Electrical Enzineering, University of Washington, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Enzineering, University of Washington, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030096283","display_name":"Matthai Philipose","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthai Philipose","raw_affiliation_strings":["Microsoft AI and Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007425970","display_name":"Ivan Tashev","orcid":"https://orcid.org/0000-0002-2263-2047"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ivan Tashev","raw_affiliation_strings":["Microsoft AI and Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084618329","display_name":"Shuayb Zarar","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuayb Zarar","raw_affiliation_strings":["Microsoft AI and Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6651,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.67763801,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2236","last_page":"2240"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.7874774932861328},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.7084251642227173},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6515529751777649},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5601485371589661},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.52755206823349},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5235421657562256},{"id":"https://openalex.org/keywords/activity-detection","display_name":"Activity detection","score":0.5014822483062744},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.49568402767181396},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.46520382165908813},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41998106241226196},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3864045739173889},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3524649143218994},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2450910210609436},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08278638124465942}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7874774932861328},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.7084251642227173},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6515529751777649},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5601485371589661},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.52755206823349},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5235421657562256},{"id":"https://openalex.org/C2988656282","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity detection","level":2,"score":0.5014822483062744},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.49568402767181396},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.46520382165908813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41998106241226196},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3864045739173889},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3524649143218994},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2450910210609436},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08278638124465942},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"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/icassp.2018.8462127","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1841592590","https://openalex.org/W1985242443","https://openalex.org/W1994244061","https://openalex.org/W1999454387","https://openalex.org/W2048497537","https://openalex.org/W2109000787","https://openalex.org/W2110992439","https://openalex.org/W2122647985","https://openalex.org/W2129120544","https://openalex.org/W2153897396","https://openalex.org/W2165630397","https://openalex.org/W2181607856","https://openalex.org/W2197404611","https://openalex.org/W2260663238","https://openalex.org/W2319920447","https://openalex.org/W2524428287","https://openalex.org/W2525098248","https://openalex.org/W2604700561","https://openalex.org/W2618825466","https://openalex.org/W3001665736","https://openalex.org/W4295262505","https://openalex.org/W6638783484","https://openalex.org/W6650031217","https://openalex.org/W6662592111","https://openalex.org/W6676486045","https://openalex.org/W6683989643","https://openalex.org/W6686045668","https://openalex.org/W6693397755","https://openalex.org/W6727208969","https://openalex.org/W6727693893","https://openalex.org/W6736166019","https://openalex.org/W6738603831"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340","https://openalex.org/W4229451372"],"abstract_inverted_index":{"Fast":[0],"and":[1,61,67,125],"robust":[2],"voice-activity":[3,70,119],"detection":[4],"is":[5],"critical":[6],"to":[7,15,91],"efficiently":[8],"process":[9],"speech.":[10],"While":[11],"deep-learning":[12],"based":[13],"methods":[14],"detect":[16],"voice":[17],"have":[18],"shown":[19],"competitive":[20],"accuracies,":[21],"the":[22,26,50,54,58,65,81,88,93,116],"best":[23],"models":[24],"in":[25],"literature":[27],"incur":[28],"over":[29],"a":[30,74],"100":[31],"ms":[32],"latency":[33],"on":[34,63,73],"commodity":[35],"processors.":[36],"Such":[37],"delays":[38],"are":[39],"unacceptable":[40],"for":[41],"real-time":[42],"speech":[43],"processing.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48,77,104],"study":[49],"impact":[51],"of":[52,57,69],"lowering":[53],"representation":[55],"precision":[56],"neural-network":[59],"weights":[60],"neurons":[62],"both":[64],"accuracy":[66],"delay":[68,124],"detection.":[71],"Based":[72],"design-space":[75],"exploration,":[76],"not":[78],"only":[79],"determine":[80],"optimal":[82],"scaling":[83],"strategy":[84],"but":[85],"also":[86],"adjust":[87],"network":[89],"structure":[90],"accommodate":[92],"new":[94],"quantization":[95],"levels.":[96],"Through":[97],"experiments":[98],"conducted":[99],"with":[100,111,121],"real":[101],"user":[102],"data,":[103],"demonstrate":[105],"that":[106],"optimized":[107],"deep":[108],"neural":[109],"networks":[110],"lower":[112,123,127],"bit":[113],"precisions":[114],"outperform":[115],"state-of-the-art":[117],"WebRTC":[118],"detector":[120],"87x":[122],"6.8%":[126],"error":[128],"rate.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}