{"id":"https://openalex.org/W3206716742","doi":"https://doi.org/10.1109/icassp43922.2022.9747107","title":"Streaming on-Device Detection of Device Directed Speech from Voice and Touch-Based Invocation","display_name":"Streaming on-Device Detection of Device Directed Speech from Voice and Touch-Based Invocation","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3206716742","doi":"https://doi.org/10.1109/icassp43922.2022.9747107","mag":"3206716742"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747107","doi":"https://doi.org/10.1109/icassp43922.2022.9747107","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747107","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5038571306","display_name":"Ognjen Oggi Rudovic","orcid":"https://orcid.org/0000-0003-1165-6075","observed_orcids":["https://orcid.org/0000-0003-1165-6075"]},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ognjen Oggi Rudovic","raw_affiliation_strings":["Apple Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple Inc","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083649574","display_name":"Akanksha Bindal","orcid":"https://orcid.org/0009-0003-2698-3201","observed_orcids":["https://orcid.org/0009-0003-2698-3201"]},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Akanksha Bindal","raw_affiliation_strings":["Apple Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple Inc","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083789644","display_name":"Vineet Garg","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vineet Garg","raw_affiliation_strings":["Apple Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple Inc","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006330185","display_name":"Pramod Simha","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pramod Simha","raw_affiliation_strings":["Apple Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple Inc","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063425263","display_name":"Pranay Dighe","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pranay Dighe","raw_affiliation_strings":["Apple Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple Inc","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065814281","display_name":"Sachin S. Kajarekar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sachin Kajarekar","raw_affiliation_strings":["Apple Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple Inc","institution_ids":["https://openalex.org/I4210153776"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210153776"],"apc_list":null,"apc_paid":null,"fwci":0.4271,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.58139384,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"491","last_page":"495"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9746000170707703,"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":0.9746000170707703,"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":0.01269999984651804,"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/T12031","display_name":"Speech and dialogue systems","score":0.009100000374019146,"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/temporal-convolutional-network","display_name":"temporal convolutional network","score":0.9819999933242798},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"keyword spotting","score":0.6240000128746033},{"id":"https://openalex.org/keywords/memory-efficiency","display_name":"memory efficiency","score":0.32100000977516174}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8723031282424927},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.6807142496109009},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.6080541610717773},{"id":"https://openalex.org/C150594956","wikidata":"https://www.wikidata.org/wiki/Q1334829","display_name":"Wearable computer","level":2,"score":0.5658011436462402},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.45136263966560364},{"id":"https://openalex.org/C54290928","wikidata":"https://www.wikidata.org/wiki/Q4845080","display_name":"Wearable technology","level":3,"score":0.4472278356552124},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.42577964067459106},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4118284285068512},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.19380900263786316},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.14952591061592102},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0852789580821991},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747107","doi":"https://doi.org/10.1109/icassp43922.2022.9747107","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747107","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2064675550","https://openalex.org/W2407023693","https://openalex.org/W2510642588","https://openalex.org/W2626778328","https://openalex.org/W2792764867","https://openalex.org/W2797759721","https://openalex.org/W2887080793","https://openalex.org/W2891267443","https://openalex.org/W2891722048","https://openalex.org/W2944356707","https://openalex.org/W2964110616","https://openalex.org/W2964121744","https://openalex.org/W2973226577","https://openalex.org/W3001493895","https://openalex.org/W3007433671","https://openalex.org/W3047602798","https://openalex.org/W3095389792","https://openalex.org/W3097330909","https://openalex.org/W3141500890","https://openalex.org/W3161145038","https://openalex.org/W3162664104","https://openalex.org/W3163237592","https://openalex.org/W3198039885","https://openalex.org/W3198061281","https://openalex.org/W6801193894"],"related_works":["https://openalex.org/W4372260078","https://openalex.org/W3161145038","https://openalex.org/W4297841617","https://openalex.org/W3162664104","https://openalex.org/W3199975244","https://openalex.org/W3141500890","https://openalex.org/W7153129411","https://openalex.org/W4281608390","https://openalex.org/W2887080793","https://openalex.org/W2949738301"],"abstract_inverted_index":{"When":[0],"interacting":[1],"with":[2,138,164,181,192],"smart":[3],"devices":[4],"such":[5],"as":[6],"mobile-phones":[7],"or":[8,22,44,179],"wearables,":[9],"the":[10,28,34,41,75,82,95,109,116,154,165,171,182,199],"user":[11,53],"typically":[12],"invokes":[13],"a":[14,20,25,88,131,158,209],"virtual":[15],"assistant":[16],"(VA)":[17],"by":[18,23,40],"saying":[19],"keyword":[21],"pressing":[24],"button":[26,46],"on":[27,52,142],"device.":[29],"However,":[30],"in":[31,130,161,189,195],"many":[32],"cases,":[33],"VA":[35],"can":[36,120],"accidentally":[37],"be":[38],"invoked":[39],"keyword-like":[42],"speech":[43,70,123,187],"accidental":[45],"press,":[47],"which":[48],"may":[49],"have":[50],"implications":[51],"experience":[54],"and":[55,77,146,149,168,191],"privacy.":[56],"To":[57,80,108],"this":[58,114,136],"end,":[59],"we":[60,86],"propose":[61],"an":[62],"acoustic":[63],"false-trigger-mitigation":[64],"(FTM)":[65],"approach":[66,118,137,201],"for":[67,104],"on-device":[68],"device-directed":[69,122],"detection":[71],"that":[72,119,152,170],"simultaneously":[73],"handles":[74],"voice-trigger":[76],"touch-based":[78],"invocation.":[79],"facilitate":[81],"model":[83],"deployment":[84],"on-device,":[85],"introduce":[87],"new":[89],"streaming":[90,132,139,174],"decision":[91],"layer,":[92,145],"derived":[93],"using":[94],"notion":[96],"of":[97,111,202],"temporal":[98],"convolutional":[99],"networks":[100],"(TCN)":[101],"[1],":[102],"known":[103],"their":[105],"computational":[106],"efficiency.":[107],"best":[110],"our":[112],"knowledge,":[113],"is":[115],"first":[117],"detect":[121],"from":[124],"more":[125],"than":[126],"one":[127],"invocation":[128],"type":[129],"fashion.":[133],"We":[134],"compare":[135],"alternatives":[140],"based":[141],"vanilla":[143],"Average":[144],"canonical":[147],"LSTMs,":[148],"show:":[150],"(i)":[151],"all":[153],"models":[155],"show":[156],"only":[157],"small":[159],"degradation":[160],"accuracy":[162],"compared":[163,207],"invocation-specific":[166],"models,":[167],"(ii)":[169],"newly":[172],"introduced":[173],"TCN":[175],"consistently":[176],"performs":[177],"better":[178],"comparable":[180],"alternatives,":[183],"while":[184],"mitigating":[185],"device-undirected":[186],"faster":[188],"time,":[190],"(relative)":[193],"reduction":[194],"runtime":[196],"peak-memory":[197],"over":[198],"LSTM-based":[200],"33%":[203],"vs.":[204],"7%,":[205],"when":[206],"to":[208],"non-streaming":[210],"counterpart.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2021-10-25T00:00:00"}
