{"id":"https://openalex.org/W3095012737","doi":"https://doi.org/10.21437/interspeech.2020-3177","title":"Small-Footprint Keyword Spotting with Multi-Scale Temporal Convolution","display_name":"Small-Footprint Keyword Spotting with Multi-Scale Temporal Convolution","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3095012737","doi":"https://doi.org/10.21437/interspeech.2020-3177","mag":"3095012737"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-3177","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-3177","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/A5103143772","display_name":"Ximin Li","orcid":"https://orcid.org/0009-0006-5310-6636"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ximin Li","raw_affiliation_strings":["CAS Key Laboratory of Wireless-Optical Communications, University of Science and Technology of China, Hefei, P. R. China"],"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Wireless-Optical Communications, University of Science and Technology of China, Hefei, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101704710","display_name":"Xiaodong Wei","orcid":"https://orcid.org/0000-0003-3468-5792"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodong Wei","raw_affiliation_strings":["CAS Key Laboratory of Wireless-Optical Communications, University of Science and Technology of China, Hefei, P. R. China"],"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Wireless-Optical Communications, University of Science and Technology of China, Hefei, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089544297","display_name":"Xiaowei Qin","orcid":"https://orcid.org/0000-0001-7296-3461"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaowei Qin","raw_affiliation_strings":["CAS Key Laboratory of Wireless-Optical Communications, University of Science and Technology of China, Hefei, P. R. China"],"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Wireless-Optical Communications, University of Science and Technology of China, Hefei, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103143772"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":3.841,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.94592938,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1987","last_page":"1991"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9923999905586243,"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":0.9896000027656555,"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/footprint","display_name":"Footprint","score":0.7895294427871704},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7251414060592651},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6612579822540283},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6359888911247253},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.5674504637718201},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.42636778950691223},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3845931589603424},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.1496535837650299},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.13804331421852112},{"id":"https://openalex.org/keywords/archaeology","display_name":"Archaeology","score":0.051510632038116455}],"concepts":[{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.7895294427871704},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7251414060592651},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6612579822540283},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6359888911247253},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.5674504637718201},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.42636778950691223},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3845931589603424},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.1496535837650299},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.13804331421852112},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.051510632038116455},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-3177","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-3177","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W2034940213","https://openalex.org/W2194775991","https://openalex.org/W2407023693","https://openalex.org/W2507580616","https://openalex.org/W2748659049","https://openalex.org/W2769912137","https://openalex.org/W2797583228","https://openalex.org/W2889511491","https://openalex.org/W2953384591","https://openalex.org/W2963163009","https://openalex.org/W2964187693","https://openalex.org/W2973226577","https://openalex.org/W3015287265"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W3119978414","https://openalex.org/W2114097550","https://openalex.org/W3206647229","https://openalex.org/W4286904253","https://openalex.org/W2000885660","https://openalex.org/W1969408022","https://openalex.org/W2117995638","https://openalex.org/W1989658893","https://openalex.org/W2545741539"],"abstract_inverted_index":{"Keyword":[0],"Spotting":[1],"(KWS)":[2],"plays":[3],"a":[4,49,55,80],"vital":[5],"role":[6],"in":[7],"human-computer":[8],"interaction":[9],"for":[10,29,88,109],"smart":[11],"on-device":[12],"terminals":[13],"and":[14,26,77,132],"service":[15],"robots.It":[16],"remains":[17],"challenging":[18],"to":[19,42,122,138],"achieve":[20],"the":[21,36,43,94,113,116,123,139,158],"trade-off":[22],"between":[23],"small":[24],"footprint":[25],"high":[27],"accuracy":[28,159],"KWS":[30,89],"task.In":[31],"this":[32],"paper,":[33],"we":[34,97],"explore":[35],"application":[37],"of":[38,59,75,151,160],"multi-scale":[39],"temporal":[40,51,61,70,76,81,100],"modeling":[41],"smallfootprint":[44],"keyword":[45],"spotting":[46],"task.We":[47],"propose":[48],"multi-branch":[50],"convolution":[52,62,101,125],"module":[53],"(MTConv),":[54],"CNN":[56],"block":[57],"consisting":[58],"multiple":[60],"filters":[63],"with":[64,103,155,162],"different":[65],"kernel":[66],"sizes,":[67],"which":[68],"enriches":[69],"feature":[71],"space.Besides,":[72],"taking":[73],"advantage":[74],"depthwise":[78],"convolution,":[79],"efficient":[82],"neural":[83],"network":[84],"(TENet)":[85],"is":[86],"designed":[87],"system":[90],"1":[91],".Based":[92],"on":[93,143],"purposed":[95],"model,":[96],"replace":[98],"standard":[99],"layers":[102],"MTConvs":[104],"that":[105,128,149],"can":[106,118],"be":[107,119],"trained":[108,154],"better":[110],"performance.While":[111],"at":[112],"inference":[114],"stage,":[115],"MTConv":[117,156],"equivalently":[120],"converted":[121],"base":[124,140],"architecture,":[126],"so":[127],"no":[129],"extra":[130],"parameters":[131],"computational":[133],"costs":[134],"are":[135],"added":[136],"compared":[137],"model.The":[141],"results":[142],"Google":[144],"Speech":[145],"Command":[146],"Dataset":[147],"show":[148],"one":[150],"our":[152],"models":[153],"performs":[157],"96.8%":[161],"only":[163],"100K":[164],"parameters.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-29T08:15:47.926485","created_date":"2025-10-10T00:00:00"}