{"id":"https://openalex.org/W4205299633","doi":"https://doi.org/10.1109/ic-nidc54101.2021.9660544","title":"An Efficient Temporal Model for Small-Footprint Keyword Spotting","display_name":"An Efficient Temporal Model for Small-Footprint Keyword Spotting","publication_year":2021,"publication_date":"2021-11-17","ids":{"openalex":"https://openalex.org/W4205299633","doi":"https://doi.org/10.1109/ic-nidc54101.2021.9660544"},"language":"en","primary_location":{"id":"doi:10.1109/ic-nidc54101.2021.9660544","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ic-nidc54101.2021.9660544","pdf_url":null,"source":{"id":"https://openalex.org/S4363608589","display_name":"2021 7th IEEE International Conference on Network Intelligence and Digital Content (IC-NIDC)","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":"2021 7th IEEE International Conference on Network Intelligence and Digital Content (IC-NIDC)","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/A5100379616","display_name":"Shuo Zhang","orcid":"https://orcid.org/0000-0003-4622-0669"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuo Zhang","raw_affiliation_strings":["USTB-EEasyTech Joint Lab of Artificial Intelligence, Beijing, China","University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"USTB-EEasyTech Joint Lab of Artificial Intelligence, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]},{"raw_affiliation_string":"University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669565","display_name":"Tianhao Zhang","orcid":"https://orcid.org/0000-0002-5939-3932"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianhao Zhang","raw_affiliation_strings":["USTB-EEasyTech Joint Lab of Artificial Intelligence, Beijing, China","University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"USTB-EEasyTech Joint Lab of Artificial Intelligence, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]},{"raw_affiliation_string":"University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006074341","display_name":"Song-Lu Chen","orcid":"https://orcid.org/0000-0002-0780-658X"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songlu Chen","raw_affiliation_strings":["University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352754","display_name":"Feng Chen","orcid":"https://orcid.org/0000-0003-4813-2494"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Chen","raw_affiliation_strings":["EEasy Technology Company Ltd, Zhuhai, China","USTB-EEasyTech Joint Lab of Artificial Intelligence, Beijing, China"],"affiliations":[{"raw_affiliation_string":"EEasy Technology Company Ltd, Zhuhai, China","institution_ids":[]},{"raw_affiliation_string":"USTB-EEasyTech Joint Lab of Artificial Intelligence, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074514262","display_name":"Xu-Cheng Yin","orcid":"https://orcid.org/0000-0003-0023-0220"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xucheng Yin","raw_affiliation_strings":["USTB-EEasyTech Joint Lab of Artificial Intelligence, Beijing, China","University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"USTB-EEasyTech Joint Lab of Artificial Intelligence, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]},{"raw_affiliation_string":"University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100379616"],"corresponding_institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I92403157"],"apc_list":null,"apc_paid":null,"fwci":0.1257,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.3874556,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"289","last_page":"293"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.9474939107894897},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8782435655593872},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.8014476299285889},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.639529824256897},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.5785860419273376},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5393959879875183},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.535385251045227},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.519203245639801},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.513966977596283},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4940333962440491},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.46619361639022827},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4169081449508667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3742844760417938},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.0964842438697815}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9474939107894897},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8782435655593872},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.8014476299285889},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.639529824256897},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.5785860419273376},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5393959879875183},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.535385251045227},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.519203245639801},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.513966977596283},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4940333962440491},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.46619361639022827},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4169081449508667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3742844760417938},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0964842438697815},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ic-nidc54101.2021.9660544","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ic-nidc54101.2021.9660544","pdf_url":null,"source":{"id":"https://openalex.org/S4363608589","display_name":"2021 7th IEEE International Conference on Network Intelligence and Digital Content (IC-NIDC)","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":"2021 7th IEEE International Conference on Network Intelligence and Digital Content (IC-NIDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W114193738","https://openalex.org/W1522301498","https://openalex.org/W1544266773","https://openalex.org/W1582723958","https://openalex.org/W1997449813","https://openalex.org/W1999121090","https://openalex.org/W2015688877","https://openalex.org/W2034940213","https://openalex.org/W2056986588","https://openalex.org/W2122797512","https://openalex.org/W2148154194","https://openalex.org/W2156431836","https://openalex.org/W2194775991","https://openalex.org/W2292087804","https://openalex.org/W2407023693","https://openalex.org/W2507319753","https://openalex.org/W2507580616","https://openalex.org/W2587529061","https://openalex.org/W2748659049","https://openalex.org/W2752782242","https://openalex.org/W2769912137","https://openalex.org/W2797583228","https://openalex.org/W2889511491","https://openalex.org/W2962707338","https://openalex.org/W2964187693","https://openalex.org/W2972792496","https://openalex.org/W3019293601","https://openalex.org/W3098773154","https://openalex.org/W6631190155","https://openalex.org/W6632425017","https://openalex.org/W6634592987","https://openalex.org/W6696449567","https://openalex.org/W6746451879","https://openalex.org/W6750665317"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W3119978414","https://openalex.org/W2114097550","https://openalex.org/W2388033618","https://openalex.org/W2516975559","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W4286904253","https://openalex.org/W2000885660","https://openalex.org/W2117995638"],"abstract_inverted_index":{"Keyword":[0],"spotting":[1],"(KWS),":[2],"as":[3],"an":[4],"essential":[5],"part":[6],"of":[7,21,96,101,157],"human-computer":[8],"interaction,":[9],"is":[10],"widely":[11],"used":[12],"in":[13,72,79],"mobile":[14],"device":[15],"terminals.":[16],"However,":[17,37],"the":[18,64,97,102,112,118,129,137,148,153,174],"hardware":[19],"resources":[20],"these":[22,30],"devices":[23,31],"are":[24,77],"usually":[25],"limited,":[26],"so":[27],"running":[28,65],"on":[29,85,147],"requires":[32],"a":[33,53,69,80,107],"small":[34],"memory":[35],"footprint.":[36],"previous":[38],"works":[39],"still":[40],"need":[41],"massive":[42],"parameters":[43,165,176],"to":[44,62,92,110],"achieve":[45],"high":[46],"performance.":[47],"In":[48],"this":[49],"work,":[50],"we":[51,67,105,124],"propose":[52],"context-dependent":[54],"and":[55,116,120,136,166,177],"compact":[56],"network":[57,89],"for":[58],"small-footprint":[59],"KWS.":[60],"Firstly,":[61],"reduce":[63],"time,":[66],"apply":[68],"sub-sampling":[70],"technique":[71],"which":[73,169],"hidden":[74],"activation":[75],"values":[76],"calculated":[78],"few":[81],"time":[82,86],"steps":[83],"based":[84],"delay":[87],"neural":[88],"(TDNN).":[90],"Secondly,":[91],"take":[93],"full":[94],"advantage":[95],"global":[98],"context":[99],"information":[100],"feature":[103],"maps,":[104],"utilize":[106],"squeeze-and-excitation":[108],"block":[109],"emphasize":[111],"most":[113],"discriminating":[114],"area":[115],"distinguish":[117],"speech":[119],"non-speech":[121],"regions.":[122],"Finally,":[123],"conduct":[125],"extensive":[126],"experiments":[127],"with":[128,162,173],"publicly":[130],"available":[131],"Google":[132],"Speech":[133,141],"Commands":[134,142],"dataset":[135,150],"private":[138],"Biaobei":[139],"Chinese":[140],"dataset.":[143],"The":[144],"experimental":[145],"results":[146],"public":[149],"verify":[151],"that":[152],"classification":[154],"error":[155],"rate":[156],"our":[158],"method":[159],"reaches":[160],"3.56%":[161],"only":[163],"11K":[164],"322K":[167],"multiplications,":[168],"achieves":[170],"state-of-the-art":[171],"performance":[172],"fewest":[175],"multiplications.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}