{"id":"https://openalex.org/W3025581723","doi":"https://doi.org/10.21437/interspeech.2020-1003","title":"Streaming Keyword Spotting on Mobile Devices","display_name":"Streaming Keyword Spotting on Mobile Devices","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3025581723","doi":"https://doi.org/10.21437/interspeech.2020-1003","mag":"3025581723"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1003","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1003","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2005.06720","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103149673","display_name":"Oleg Rybakov","orcid":"https://orcid.org/0009-0007-0021-047X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Oleg Rybakov","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077568955","display_name":"Natasha Kononenko","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Natasha Kononenko","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021522143","display_name":"Niranjan Subrahmanya","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Niranjan Subrahmanya","raw_affiliation_strings":["Google Speech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Speech","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025237352","display_name":"Mirk\u00f3 Visontai","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mirk\u00f3 Visontai","raw_affiliation_strings":["Google Speech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Speech","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071613306","display_name":"Stella Laurenzo","orcid":"https://orcid.org/0000-0001-5806-4611"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stella Laurenzo","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103149673"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":11.2874,"has_fulltext":false,"cited_by_count":112,"citation_normalized_percentile":{"value":0.98761774,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2277","last_page":"2281"},"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/T11309","display_name":"Music and Audio Processing","score":0.9966999888420105,"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/T10028","display_name":"Topic Modeling","score":0.9958000183105469,"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/keyword-spotting","display_name":"Keyword spotting","score":0.8721118569374084},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8697609901428223},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6113216876983643},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.5589146018028259},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.5579372644424438},{"id":"https://openalex.org/keywords/rewriting","display_name":"Rewriting","score":0.5131850838661194},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5038267970085144},{"id":"https://openalex.org/keywords/real-time-streaming-protocol","display_name":"Real Time Streaming Protocol","score":0.4926775097846985},{"id":"https://openalex.org/keywords/streaming-data","display_name":"Streaming data","score":0.48454681038856506},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.4230513274669647},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4171863794326782},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3696039021015167},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3407169580459595},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.31941282749176025},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.17621329426765442},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.13733473420143127},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09495028853416443},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.09247511625289917}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.8721118569374084},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8697609901428223},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6113216876983643},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.5589146018028259},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.5579372644424438},{"id":"https://openalex.org/C154690210","wikidata":"https://www.wikidata.org/wiki/Q1668499","display_name":"Rewriting","level":2,"score":0.5131850838661194},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5038267970085144},{"id":"https://openalex.org/C110738861","wikidata":"https://www.wikidata.org/wiki/Q682598","display_name":"Real Time Streaming Protocol","level":3,"score":0.4926775097846985},{"id":"https://openalex.org/C2777611316","wikidata":"https://www.wikidata.org/wiki/Q39045282","display_name":"Streaming data","level":2,"score":0.48454681038856506},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.4230513274669647},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4171863794326782},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3696039021015167},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3407169580459595},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31941282749176025},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.17621329426765442},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.13733473420143127},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09495028853416443},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.09247511625289917},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2020-1003","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1003","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2005.06720","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.06720","pdf_url":"https://arxiv.org/pdf/2005.06720","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2005.06720","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.06720","pdf_url":"https://arxiv.org/pdf/2005.06720","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1724438581","https://openalex.org/W2034940213","https://openalex.org/W2064675550","https://openalex.org/W2112796928","https://openalex.org/W2121029939","https://openalex.org/W2133564696","https://openalex.org/W2148154194","https://openalex.org/W2157331557","https://openalex.org/W2407023693","https://openalex.org/W2602634800","https://openalex.org/W2612445135","https://openalex.org/W2769912137","https://openalex.org/W2797583228","https://openalex.org/W2888641632","https://openalex.org/W2930364467","https://openalex.org/W2936774411","https://openalex.org/W2950635152","https://openalex.org/W2953219395","https://openalex.org/W2962760690","https://openalex.org/W2963122961","https://openalex.org/W2963403868","https://openalex.org/W2963628261","https://openalex.org/W2963977978","https://openalex.org/W2964308564","https://openalex.org/W2973226577","https://openalex.org/W3015399080","https://openalex.org/W3017216675","https://openalex.org/W3097018422","https://openalex.org/W3098773154","https://openalex.org/W4297775537","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W3119978414","https://openalex.org/W4286904253","https://openalex.org/W2516975559","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2117995638"],"abstract_inverted_index":{"In":[0],"this":[1,61,82],"work":[2],"we":[3,84],"explore":[4,108],"the":[5,30,37,47,117,121],"latency":[6,103],"and":[7,16,34,50,92,98,104],"accuracy":[8],"of":[9,46,72],"keyword":[10],"spotting":[11],"(KWS)":[12],"models":[13,74,88,111],"in":[14,89],"streaming":[15,41,76,91,133],"non-streaming":[17,26,73,93],"modes":[18,94],"on":[19,95,125],"mobile":[20,96],"phones.":[21],"NN":[22],"model":[23,57],"conversion":[24,71],"from":[25],"mode":[27,42],"(model":[28,43],"receives":[29,44],"whole":[31],"input":[32,48],"sequence":[33,49],"then":[35],"returns":[36],"classification":[38,118],"result)":[39],"to":[40,75],"portion":[45],"classifies":[51],"it":[52],"incrementally)":[53],"may":[54],"require":[55],"manual":[56],"rewriting.":[58],"We":[59,106],"address":[60],"by":[62,123],"designing":[63],"a":[64],"Tensorflow/Keras":[65],"based":[66],"library":[67,83,134],"which":[68,115],"allows":[69],"automatic":[70],"ones":[77],"with":[78,112,135],"minimum":[79],"effort.":[80],"With":[81],"benchmark":[85],"multiple":[86],"KWS":[87,110],"both":[90],"phones":[97],"demonstrate":[99],"different":[100],"tradeoffs":[101],"between":[102],"accuracy.":[105],"also":[107],"novel":[109],"multi-head":[113],"attention":[114],"reduce":[116],"error":[119],"over":[120],"state-of-art":[122],"10%":[124],"Google":[126],"speech":[127],"commands":[128],"data":[129],"sets":[130],"V2.":[131],"The":[132],"all":[136],"experiments":[137],"is":[138],"open-sourced.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":32},{"year":2022,"cited_by_count":22},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":4}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}
