{"id":"https://openalex.org/W3096831963","doi":"https://doi.org/10.21437/interspeech.2020-2763","title":"Stacked 1D Convolutional Networks for End-to-End Small Footprint Voice Trigger Detection","display_name":"Stacked 1D Convolutional Networks for End-to-End Small Footprint Voice Trigger Detection","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096831963","doi":"https://doi.org/10.21437/interspeech.2020-2763","mag":"3096831963"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2763","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2763","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":["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/A5101768343","display_name":"Takuya Higuchi","orcid":"https://orcid.org/0000-0002-0361-7132"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Takuya Higuchi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050579078","display_name":"Mohammad Ghasemzadeh","orcid":"https://orcid.org/0000-0002-6805-4852"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammad Ghasemzadeh","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111475467","display_name":"Kisun You","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kisun You","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5110720542","display_name":"Chandra Dhir","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chandra Dhir","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101768343"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.273,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.89032258,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2592","last_page":"2596"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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":0.9930999875068665,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.8788426518440247},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.6695978045463562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.611711859703064},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.33149880170822144},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.10659825801849365}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8788426518440247},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.6695978045463562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.611711859703064},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.33149880170822144},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.10659825801849365},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2763","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2763","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1485222997","https://openalex.org/W1522301498","https://openalex.org/W1553469512","https://openalex.org/W2034940213","https://openalex.org/W2295405790","https://openalex.org/W2407023693","https://openalex.org/W2507319753","https://openalex.org/W2507580616","https://openalex.org/W2748659049","https://openalex.org/W2775572503","https://openalex.org/W2787752687","https://openalex.org/W2797759721","https://openalex.org/W2889511491","https://openalex.org/W2891722048","https://openalex.org/W2953219395","https://openalex.org/W2962707338","https://openalex.org/W4309147820"],"related_works":["https://openalex.org/W2130966263","https://openalex.org/W2938873567","https://openalex.org/W2096935214","https://openalex.org/W2312526371","https://openalex.org/W2049680545","https://openalex.org/W3002436306","https://openalex.org/W2010256098","https://openalex.org/W3096831963","https://openalex.org/W4327778771","https://openalex.org/W2102081799"],"abstract_inverted_index":{"We":[0],"propose":[1,106],"a":[2,17,37,46,68,88,92,122,128,141,162,167],"stacked":[3],"1D":[4,123,130],"convolutional":[5],"neural":[6],"network":[7],"(S1DCNN)":[8],"for":[9,67,81,112],"end-to-end":[10,82,113],"small":[11,60],"footprint":[12],"voice":[13,47,69,83,115],"trigger":[14,20,48,70,84,116],"detection":[15,21,49,71],"in":[16],"streaming":[18],"scenario.Voice":[19],"is":[22,65],"an":[23,54,109],"important":[24],"speech":[25],"application,":[26],"with":[27,91,161],"which":[28,96],"users":[29],"can":[30,137],"activate":[31],"their":[32],"devices":[33],"by":[34,127],"simply":[35],"saying":[36],"keyword":[38],"or":[39],"phrase.Due":[40],"to":[41,172,186],"privacy":[42],"and":[43,62,166],"latency":[44],"reasons,":[45],"system":[50],"should":[51],"run":[52],"on":[53,57],"always-on":[55],"processor":[56],"device.Therefore,":[58],"having":[59],"memory":[61],"compute":[63],"cost":[64],"crucial":[66],"system.Recently,":[72],"singular":[73],"value":[74],"decomposition":[75],"filters":[76],"(SVDFs)":[77],"has":[78],"been":[79],"used":[80],"detection.The":[85],"SVDFs":[86],"approximate":[87],"fully-connected":[89],"layer":[90,119,125],"low":[93],"rank":[94],"approximation,":[95],"reduces":[97],"the":[98,135,145,151,173,179,183],"number":[99],"of":[100,121,144],"model":[101,164],"parameters.In":[102],"this":[103],"work,":[104],"we":[105],"S1DCNN":[107,118,146,152,180],"as":[108,140],"alternative":[110],"approach":[111],"small-footprint":[114],"detection.An":[117],"consists":[120],"convolution":[124,131],"followed":[126],"depth-wise":[129],"layer.We":[132],"show":[133,149],"that":[134,150],"SVDF":[136],"be":[138],"expressed":[139],"special":[142],"case":[143],"layer.Experimental":[147],"results":[148],"achieve":[153],"19.0%":[154],"relative":[155],"false":[156],"reject":[157],"ratio":[158],"(FRR)":[159],"reduction":[160],"similar":[163,168],"size":[165],"time":[169,177],"delay":[170],"compared":[171],"SVDF.By":[174],"using":[175],"longer":[176],"delays,":[178],"further":[181],"improve":[182],"FRR":[184],"up":[185],"12.2%":[187],"relative.":[188]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}