{"id":"https://openalex.org/W4283028414","doi":"https://doi.org/10.21437/interspeech.2022-10608","title":"Latency Control for Keyword Spotting","display_name":"Latency Control for Keyword Spotting","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283028414","doi":"https://doi.org/10.21437/interspeech.2022-10608"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10608","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10608","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"Interspeech 2022","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2206.07261","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042851905","display_name":"Christin Jose","orcid":"https://orcid.org/0000-0002-7594-4490"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Christin Jose","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Joe Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joe Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023708721","display_name":"Grant P. Strimel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Grant Strimel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070084977","display_name":"Mohammad Omar Khursheed","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammad Omar Khursheed","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041625765","display_name":"Yuriy Mishchenko","orcid":"https://orcid.org/0009-0006-0826-5777"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuriy Mishchenko","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5049134079","display_name":"Brian Kulis","orcid":"https://orcid.org/0000-0002-1704-3838"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brian Kulis","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5042851905"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04462819,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1891","last_page":"1895"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.29179999232292175,"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/T12031","display_name":"Speech and dialogue systems","score":0.29179999232292175,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.2797999978065491,"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/T12128","display_name":"AI in Service Interactions","score":0.10660000145435333,"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/latency","display_name":"Latency (audio)","score":0.8017447590827942},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7997967004776001},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.7779899835586548},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6720229983329773},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.4119718670845032},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.4112360179424286},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36562323570251465},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0962088406085968}],"concepts":[{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.8017447590827942},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7997967004776001},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.7779899835586548},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6720229983329773},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.4119718670845032},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.4112360179424286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36562323570251465},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0962088406085968}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2022-10608","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10608","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:null:2144/47104","is_oa":false,"landing_page_url":"http://doi.org/10.21437/interspeech.2022-10608","pdf_url":null,"source":{"id":"https://openalex.org/S4306402384","display_name":"OpenBU (Boston University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I111088046","host_organization_name":"Boston University","host_organization_lineage":["https://openalex.org/I111088046"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference materials"},{"id":"pmh:oai:arXiv.org:2206.07261","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.07261","pdf_url":"https://arxiv.org/pdf/2206.07261","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"},{"id":"doi:10.48550/arxiv.2206.07261","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2206.07261","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2206.07261","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.07261","pdf_url":"https://arxiv.org/pdf/2206.07261","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4781179","https://openalex.org/W9474471","https://openalex.org/W14635080","https://openalex.org/W4560741","https://openalex.org/W9939214","https://openalex.org/W8315361","https://openalex.org/W12861721","https://openalex.org/W10064791","https://openalex.org/W1208717","https://openalex.org/W14903543"],"abstract_inverted_index":{"Conversational":[0],"agents":[1],"commonly":[2],"utilize":[3],"keyword":[4,64],"spotting":[5],"(KWS)":[6],"to":[7,22,47,55,75,99,119,141,155],"initiate":[8],"voice":[9],"interaction":[10],"with":[11,134],"the":[12,33,63,82,120],"user.":[13],"For":[14],"user":[15],"experience":[16],"and":[17,52,79],"privacy":[18],"considerations,":[19],"existing":[20,100],"approaches":[21],"KWS":[23,49],"largely":[24],"focus":[25],"on":[26],"accuracy,":[27],"which":[28,53],"can":[29],"often":[30],"come":[31],"at":[32,149],"expense":[34],"of":[35,62],"introduced":[36],"latency.":[37],"To":[38],"address":[39],"this":[40],"tradeoff,":[41],"we":[42,86,103,138],"propose":[43],"a":[44,67,105,113,135,150],"novel":[45],"approach":[46,72,90,129],"control":[48],"model":[50],"latency":[51,78,95,115,152],"generalizes":[54],"any":[56],"loss":[57],"function":[58],"without":[59],"explicit":[60],"knowledge":[61],"endpoint.":[65],"Through":[66],"single,":[68],"tunable":[69],"hyperparameter,":[70],"our":[71,89,128],"enables":[73],"one":[74],"balance":[76],"detection":[77],"accuracy":[80],"for":[81,112],"targeted":[83],"application.":[84],"Empirically,":[85],"show":[87,125],"that":[88,126],"gives":[91],"superior":[92],"performance":[93],"under":[94],"constraints":[96],"when":[97,117,127,153],"compared":[98,118,154],"methods.":[101],"Namely,":[102],"make":[104],"substantial":[106],"25\\%":[107],"relative":[108,143],"false":[109,144],"accepts":[110,145],"improvement":[111],"fixed":[114,151],"target":[116],"baseline":[121],"state-of-the-art.":[122],"We":[123],"also":[124],"is":[130],"used":[131],"in":[132],"conjunction":[133],"max-pooling":[136],"loss,":[137],"are":[139],"able":[140],"improve":[142],"by":[146],"25":[147],"%":[148],"cross":[156],"entropy":[157],"loss.":[158]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2022-06-18T00:00:00"}