{"id":"https://openalex.org/W4280541836","doi":"https://doi.org/10.1142/s0218001422580034","title":"Small-Footprint Keyword Spotting Based on Gated Channel Transformation Sandglass Residual Neural Network","display_name":"Small-Footprint Keyword Spotting Based on Gated Channel Transformation Sandglass Residual Neural Network","publication_year":2022,"publication_date":"2022-05-12","ids":{"openalex":"https://openalex.org/W4280541836","doi":"https://doi.org/10.1142/s0218001422580034"},"language":"en","primary_location":{"id":"doi:10.1142/s0218001422580034","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001422580034","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-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/A5104103663","display_name":"Ying Zhang","orcid":"https://orcid.org/0000-0002-8812-2955"},"institutions":[{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Zhang","raw_affiliation_strings":["Key Laboratory of Advanced Design and Intelligent Computing, Ministry of Education, Dalian University, Dalian, Liaoning, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Advanced Design and Intelligent Computing, Ministry of Education, Dalian University, Dalian, Liaoning, P. R. China","institution_ids":["https://openalex.org/I4210092944"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100950657","display_name":"Shirong Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shirong Zhu","raw_affiliation_strings":["Key Laboratory of Advanced Design and Intelligent Computing, Ministry of Education, Dalian University, Dalian, Liaoning, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Advanced Design and Intelligent Computing, Ministry of Education, Dalian University, Dalian, Liaoning, P. R. China","institution_ids":["https://openalex.org/I4210092944"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101776596","display_name":"Chao Yu","orcid":"https://orcid.org/0000-0002-9775-8402"},"institutions":[{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Yu","raw_affiliation_strings":["Key Laboratory of Advanced Design and Intelligent Computing, Ministry of Education, Dalian University, Dalian, Liaoning, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Advanced Design and Intelligent Computing, Ministry of Education, Dalian University, Dalian, Liaoning, P. R. China","institution_ids":["https://openalex.org/I4210092944"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049831969","display_name":"Lasheng Zhao","orcid":"https://orcid.org/0000-0003-3003-7085"},"institutions":[{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lasheng Zhao","raw_affiliation_strings":["Key Laboratory of Advanced Design and Intelligent Computing, Ministry of Education, Dalian University, Dalian, Liaoning, P. R. China"],"raw_orcid":"https://orcid.org/0000-0003-3003-7085","affiliations":[{"raw_affiliation_string":"Key Laboratory of Advanced Design and Intelligent Computing, Ministry of Education, Dalian University, Dalian, Liaoning, P. R. China","institution_ids":["https://openalex.org/I4210092944"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5049831969"],"corresponding_institution_ids":["https://openalex.org/I4210092944"],"apc_list":null,"apc_paid":null,"fwci":0.4647,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.67741902,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"36","issue":"07","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":0.9998999834060669,"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":0.9998999834060669,"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":0.9984999895095825,"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/T10028","display_name":"Topic Modeling","score":0.9919999837875366,"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/computer-science","display_name":"Computer science","score":0.834485650062561},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6853988170623779},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.670759916305542},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6632264256477356},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5635778307914734},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.5623802542686462},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5564548969268799},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4982576370239258},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.49341192841529846},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4870586693286896},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.47412967681884766},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4210902750492096},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4180550277233124},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4116500914096832},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11659809947013855}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.834485650062561},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6853988170623779},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.670759916305542},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6632264256477356},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5635778307914734},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.5623802542686462},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5564548969268799},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4982576370239258},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.49341192841529846},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4870586693286896},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.47412967681884766},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4210902750492096},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4180550277233124},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4116500914096832},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11659809947013855},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218001422580034","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001422580034","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2563840566","display_name":null,"funder_award_id":"No. XLYC2008017","funder_id":"https://openalex.org/F4320329895","funder_display_name":"Liaoning Revitalization Talents Program"}],"funders":[{"id":"https://openalex.org/F4320329895","display_name":"Liaoning Revitalization Talents Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2034940213","https://openalex.org/W2194775991","https://openalex.org/W2531409750","https://openalex.org/W2604414494","https://openalex.org/W2748659049","https://openalex.org/W2767072113","https://openalex.org/W2889511491","https://openalex.org/W2963163009","https://openalex.org/W2964187693","https://openalex.org/W3003903817","https://openalex.org/W3015287265","https://openalex.org/W3015537910","https://openalex.org/W3035502324","https://openalex.org/W3096193467","https://openalex.org/W3109821366","https://openalex.org/W3111277624","https://openalex.org/W3113272803","https://openalex.org/W3114569701","https://openalex.org/W3123598112","https://openalex.org/W3124055213","https://openalex.org/W3147206993","https://openalex.org/W3159502203","https://openalex.org/W3163438373"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W4286904253","https://openalex.org/W3119978414","https://openalex.org/W2516975559","https://openalex.org/W3206647229","https://openalex.org/W4408353962","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2545741539"],"abstract_inverted_index":{"Keyword":[0],"spotting":[1],"plays":[2],"a":[3],"crucial":[4],"role":[5],"in":[6,176],"realizing":[7],"voice-based":[8],"user":[9],"interaction":[10],"on":[11,78,107,123],"intelligent":[12],"equipment":[13],"terminals":[14],"and":[15,31,99,104,162,183],"service":[16],"robots.":[17],"In":[18],"this":[19,37],"task,":[20],"it":[21],"remains":[22],"challenging":[23],"to":[24,64,75],"achieve":[25],"the":[26,51,73,79,86,91,94,101,108,113,146,150,178],"balance":[27],"between":[28],"low":[29,181],"memory":[30,182],"high":[32,184],"precision.":[33,185],"To":[34],"better":[35],"satisfy":[36],"requirement,":[38],"we":[39],"propose":[40],"an":[41,134],"end-to-end":[42],"neural":[43],"architecture":[44],"with":[45,50,82,140,145,149],"sandglass":[46,57],"residual":[47,58],"blocks":[48,59],"embedded":[49],"gated":[52,87],"channel-wise":[53],"attention":[54,88],"mechanism.":[55],"The":[56,120],"utilize":[60],"1D":[61],"separable":[62],"convolutions":[63],"extract":[65],"bottleneck":[66],"temporal":[67,97],"features,":[68],"which":[69],"can":[70],"effectively":[71],"drive":[72],"model":[74,92,132,154],"focus":[76,106],"more":[77],"speech":[80,96,115],"segment":[81],"lower":[83],"parameters.":[84,143],"Especially,":[85],"mechanism":[89],"helps":[90],"enhance":[93],"critical":[95],"features":[98],"suppress":[100],"useless":[102],"ones":[103],"further":[105,174],"most":[109],"important":[110],"part":[111],"of":[112,136,180],"human":[114],"region":[116],"for":[117],"keyword":[118],"spotting.":[119],"experimental":[121],"results":[122],"Google":[124],"Speech":[125],"Commands":[126],"Dataset":[127],"show":[128],"that":[129],"our":[130,153],"proposed":[131],"has":[133],"accuracy":[135,163],"97.4[Formula:":[137],"see":[138,160,168],"text]":[139,161],"only":[141],"46K":[142],"Compared":[144],"baseline":[147],"method":[148],"highest":[151],"accuracy,":[152],"parameters":[155],"are":[156],"decreased":[157],"by":[158,166],"54[Formula:":[159],"is":[164],"increased":[165],"0.8[Formula:":[167],"text].":[169],"That":[170],"makes":[171],"us":[172],"take":[173],"step":[175],"achieving":[177],"goal":[179]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}