{"id":"https://openalex.org/W4225275315","doi":"https://doi.org/10.1109/icassp43922.2022.9747243","title":"Unified Speculation, Detection, and Verification Keyword Spotting","display_name":"Unified Speculation, Detection, and Verification Keyword Spotting","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225275315","doi":"https://doi.org/10.1109/icassp43922.2022.9747243"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747243","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747243","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 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/A5103070417","display_name":"Geng-Shen Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Geng-Shen Fu","raw_affiliation_strings":["Amazon Alexa Science,Cambridge,MA,USA","Amazon Alexa Science, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa Science,Cambridge,MA,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa Science, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058266572","display_name":"Thibaud S\u00e9n\u00e9chal","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thibaud Senechal","raw_affiliation_strings":["Amazon Alexa Science,Cambridge,MA,USA","Amazon Alexa Science, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa Science,Cambridge,MA,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa Science, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004064847","display_name":"Aaron Challenner","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aaron Challenner","raw_affiliation_strings":["Amazon Alexa Science,Cambridge,MA,USA","Amazon Alexa Science, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa Science,Cambridge,MA,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa Science, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100375792","display_name":"Tao Zhang","orcid":"https://orcid.org/0000-0002-2980-6281"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Zhang","raw_affiliation_strings":["Amazon Alexa Science,Cambridge,MA,USA","Amazon Alexa Science, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa Science,Cambridge,MA,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Alexa Science, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103070417"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":0.3118,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.47791424,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"7557","last_page":"7561"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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/keyword-spotting","display_name":"Keyword spotting","score":0.9156404137611389},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8806431293487549},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.7652407884597778},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.7069094181060791},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5260294079780579},{"id":"https://openalex.org/keywords/speculation","display_name":"Speculation","score":0.483247846364975},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44176921248435974},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4256264567375183},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.417688250541687},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38718652725219727},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36137622594833374}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9156404137611389},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8806431293487549},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7652407884597778},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.7069094181060791},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5260294079780579},{"id":"https://openalex.org/C47941915","wikidata":"https://www.wikidata.org/wiki/Q107885","display_name":"Speculation","level":2,"score":0.483247846364975},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44176921248435974},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4256264567375183},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.417688250541687},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38718652725219727},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36137622594833374},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747243","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747243","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2034940213","https://openalex.org/W2407023693","https://openalex.org/W2507319753","https://openalex.org/W2507580616","https://openalex.org/W2889182547","https://openalex.org/W2913340405","https://openalex.org/W2937292033","https://openalex.org/W2944817175","https://openalex.org/W2953219395","https://openalex.org/W2964187693","https://openalex.org/W2972677972","https://openalex.org/W2973226577","https://openalex.org/W3098773154","https://openalex.org/W3160521245","https://openalex.org/W3161038873","https://openalex.org/W6784807719","https://openalex.org/W6843142645"],"related_works":["https://openalex.org/W4296070214","https://openalex.org/W2171506966","https://openalex.org/W3093454656","https://openalex.org/W4283028414","https://openalex.org/W3133724979","https://openalex.org/W4252617674","https://openalex.org/W2062321506","https://openalex.org/W2100239260","https://openalex.org/W4206839609","https://openalex.org/W4225275315"],"abstract_inverted_index":{"Accurate":[0],"and":[1,32,70,82,116,186],"timely":[2],"recognition":[3],"of":[4,72],"the":[5,19,56,73,101,111,124,139,166,175],"trigger":[6,114],"keyword":[7,21,57,113,126,140],"is":[8,25],"vital":[9],"for":[10,42,155,161],"a":[11,27,50,95,118,144,152],"good":[12],"customer":[13],"experience":[14],"on":[15,100],"smart":[16],"devices.":[17],"In":[18,45,169],"traditional":[20,112],"spotting":[22,58],"task,":[23],"there":[24],"typically":[26],"trade-off":[28],"needed":[29],"between":[30],"accuracy":[31,36,69],"latency,":[33],"where":[34],"higher":[35],"can":[37,90,150,179],"be":[38,91],"achieved":[39],"by":[40,122,133,159],"waiting":[41],"more":[43,119,136],"context.":[44,127],"this":[46],"paper,":[47],"we":[48,171],"propose":[49,143],"deep":[51],"learning":[52],"model":[53,154,178],"that":[54,149,174],"separates":[55],"task":[59,115],"into":[60],"three":[61,77,157],"phases":[62],"in":[63],"order":[64],"to":[65,93,97],"further":[66],"optimize":[67],"both":[68],"latency":[71,163],"overall":[74],"system.":[75],"These":[76],"tasks":[78,158,182],"are:":[79],"Speculation,":[80],"Detection,":[81],"Verification.":[83],"Speculation":[84],"makes":[85],"an":[86],"early":[87],"decision,":[88],"which":[89],"used":[92],"give":[94],"head-start":[96],"downstream":[98],"processes":[99],"device":[102],"such":[103],"as":[104],"local":[105],"speech":[106],"recognition.":[107],"Next,":[108],"Detection":[109],"mimics":[110],"gives":[117],"accurate":[120],"decision":[121,132],"observing":[123,134],"full":[125],"Finally,":[128],"Verification":[129],"verifies":[130],"previous":[131],"even":[135],"audio":[137],"after":[138],"span.":[141],"We":[142],"latency-aware":[145],"max-pooling":[146],"loss":[147],"function":[148],"train":[151],"unified":[153,177],"these":[156,181],"tuning":[160],"different":[162],"targets":[164],"within":[165],"same":[167],"model.":[168],"addition,":[170],"empirically":[172],"show":[173],"resultant":[176],"accommodate":[180],"with":[183],"desirable":[184],"performance":[185],"without":[187],"requiring":[188],"additional":[189],"compute":[190],"or":[191],"memory":[192],"resources.":[193]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}