{"id":"https://openalex.org/W4286907583","doi":"https://doi.org/10.48550/arxiv.2110.04656","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":2021,"publication_date":"2021-10-09","ids":{"openalex":"https://openalex.org/W4286907583","doi":"https://doi.org/10.48550/arxiv.2110.04656"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2110.04656","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.04656","pdf_url":"https://arxiv.org/pdf/2110.04656","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2110.04656","any_repository_has_fulltext":true},"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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rudovic, Ognjen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bindal, Akanksha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083789644","display_name":"Vineet Garg","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Garg, Vineet","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006330185","display_name":"Pramod Simha","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simha, Pramod","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063425263","display_name":"Pranay Dighe","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dighe, Pranay","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5065814281","display_name":"Sachin S. Kajarekar","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kajarekar, Sachin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9761000275611877,"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":0.9761000275611877,"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/T12031","display_name":"Speech and dialogue systems","score":0.012000000104308128,"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":0.008899999782443047,"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/on-device-deployment","display_name":"on-device deployment","score":0.6389999985694885},{"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":0.6650000214576721}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8466655015945435},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.6818362474441528},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.6029077768325806},{"id":"https://openalex.org/C150594956","wikidata":"https://www.wikidata.org/wiki/Q1334829","display_name":"Wearable computer","level":2,"score":0.5300604701042175},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4528806805610657},{"id":"https://openalex.org/C2776527387","wikidata":"https://www.wikidata.org/wiki/Q1671839","display_name":"Invocation","level":2,"score":0.42375028133392334},{"id":"https://openalex.org/C2776898695","wikidata":"https://www.wikidata.org/wiki/Q11253473","display_name":"Smart device","level":2,"score":0.4109647274017334},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39381659030914307},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27603447437286377},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.1392817497253418},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0825495719909668},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07378840446472168},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2110.04656","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.04656","pdf_url":"https://arxiv.org/pdf/2110.04656","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2110.04656","doi":"https://doi.org/10.48550/arxiv.2110.04656","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2110.04656","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2110.04656","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.04656","pdf_url":"https://arxiv.org/pdf/2110.04656","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4286907583.pdf","grobid_xml":"https://content.openalex.org/works/W4286907583.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W2792764867","https://openalex.org/W2964121744"],"related_works":["https://openalex.org/W4372260078","https://openalex.org/W3093934775","https://openalex.org/W4297841617","https://openalex.org/W3162664104","https://openalex.org/W3199975244","https://openalex.org/W3141500890","https://openalex.org/W7153129411","https://openalex.org/W2887080793","https://openalex.org/W4281608390","https://openalex.org/W7167010685"],"abstract_inverted_index":{"When":[0],"interacting":[1],"with":[2,139,165,182,194],"smart":[3],"devices":[4],"such":[5],"as":[6],"mobile":[7],"phones":[8],"or":[9,23,45,180],"wearables,":[10],"the":[11,29,35,42,76,83,96,110,117,155,166,172,183,201],"user":[12,54],"typically":[13],"invokes":[14],"a":[15,21,26,89,132,159,211],"virtual":[16],"assistant":[17],"(VA)":[18],"by":[19,24,41],"saying":[20],"keyword":[22],"pressing":[25],"button":[27,47],"on":[28,53,143],"device.":[30],"However,":[31],"in":[32,131,162,191,197],"many":[33],"cases,":[34],"VA":[36],"can":[37,121],"accidentally":[38],"be":[39],"invoked":[40],"keyword-like":[43],"speech":[44,71,124,189],"accidental":[46],"press,":[48],"which":[49],"may":[50],"have":[51],"implications":[52],"experience":[55],"and":[56,78,147,150,169,193],"privacy.":[57],"To":[58,81,109],"this":[59,115,137],"end,":[60],"we":[61,87],"propose":[62],"an":[63],"acoustic":[64],"false-trigger-mitigation":[65],"(FTM)":[66],"approach":[67,119,138,203],"for":[68,105],"on-device":[69],"device-directed":[70,123],"detection":[72],"that":[73,120,153,171],"simultaneously":[74],"handles":[75],"voice-trigger":[77],"touch-based":[79],"invocation.":[80],"facilitate":[82],"model":[84],"deployment":[85],"on-device,":[86],"introduce":[88],"new":[90],"streaming":[91,133,140,175],"decision":[92],"layer,":[93,146],"derived":[94],"using":[95],"notion":[97],"of":[98,112,204],"temporal":[99],"convolutional":[100],"networks":[101],"(TCN)":[102],"[1],":[103],"known":[104],"their":[106],"computational":[107],"efficiency.":[108],"best":[111],"our":[113],"knowledge,":[114],"is":[116],"first":[118],"detect":[122],"from":[125],"more":[126],"than":[127],"one":[128],"invocation":[129],"type":[130],"fashion.":[134],"We":[135],"compare":[136],"alternatives":[141],"based":[142],"vanilla":[144],"Average":[145],"canonical":[148],"LSTMs,":[149],"show:":[151],"(i)":[152],"all":[154],"models":[156],"show":[157],"only":[158],"small":[160],"degradation":[161],"accuracy":[163],"compared":[164,209],"invocation-specific":[167],"models,":[168],"(ii)":[170],"newly":[173],"introduced":[174],"TCN":[176],"consistently":[177],"performs":[178],"better":[179],"comparable":[181],"alternatives,":[184],"while":[185],"mitigating":[186],"device":[187],"undirected":[188],"faster":[190],"time,":[192],"(relative)":[195],"reduction":[196],"runtime":[198],"peak-memory":[199],"over":[200],"LSTM-based":[202],"33%":[205],"vs.":[206],"7%,":[207],"when":[208],"to":[210],"non-streaming":[212],"counterpart.":[213]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2022-07-25T00:00:00"}
