{"id":"https://openalex.org/W4380479730","doi":"https://doi.org/10.1109/taslp.2023.3284523","title":"Multilingual Customized Keyword Spotting Using Similar-Pair Contrastive Learning","display_name":"Multilingual Customized Keyword Spotting Using Similar-Pair Contrastive Learning","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4380479730","doi":"https://doi.org/10.1109/taslp.2023.3284523"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3284523","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3284523","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","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/A5100381332","display_name":"Lei Lei","orcid":"https://orcid.org/0000-0001-7456-6486"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210119392","display_name":"Institute of Microelectronics","ror":"https://ror.org/02s6gs133","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Lei","raw_affiliation_strings":["Institute of Microelectronics, Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7456-6486","affiliations":[{"raw_affiliation_string":"Institute of Microelectronics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Guoshun Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210119392","display_name":"Institute of Microelectronics","ror":"https://ror.org/02s6gs133","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoshun Yuan","raw_affiliation_strings":["Institute of Microelectronics, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Microelectronics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044152359","display_name":"Hongjiang Yu","orcid":"https://orcid.org/0000-0003-0527-3676"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210119392","display_name":"Institute of Microelectronics","ror":"https://ror.org/02s6gs133","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongjiang Yu","raw_affiliation_strings":["Institute of Microelectronics, Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Microelectronics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100941191","display_name":"Dewei Kong","orcid":"https://orcid.org/0000-0002-8197-176X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210119392","display_name":"Institute of Microelectronics","ror":"https://ror.org/02s6gs133","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dewei Kong","raw_affiliation_strings":["Institute of Microelectronics, Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Microelectronics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060336310","display_name":"Yuefeng He","orcid":"https://orcid.org/0000-0002-5712-2469"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210119392","display_name":"Institute of Microelectronics","ror":"https://ror.org/02s6gs133","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuefeng He","raw_affiliation_strings":["Institute of Microelectronics, Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Microelectronics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5713,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.85871346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"2437","last_page":"2447"},"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":0.9998000264167786,"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":0.9997000098228455,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8324652910232544},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.8090472221374512},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.512766420841217},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5121304988861084},{"id":"https://openalex.org/keywords/constant-false-alarm-rate","display_name":"Constant false alarm rate","score":0.5047570466995239},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.49184203147888184},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4498370289802551},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40142107009887695},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3954369127750397},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36742210388183594}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8324652910232544},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.8090472221374512},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.512766420841217},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5121304988861084},{"id":"https://openalex.org/C77052588","wikidata":"https://www.wikidata.org/wiki/Q644307","display_name":"Constant false alarm rate","level":2,"score":0.5047570466995239},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.49184203147888184},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4498370289802551},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40142107009887695},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3954369127750397},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36742210388183594},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3284523","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3284523","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W114193738","https://openalex.org/W1494198834","https://openalex.org/W1496120315","https://openalex.org/W1522301498","https://openalex.org/W1545920196","https://openalex.org/W1549358575","https://openalex.org/W1586405805","https://openalex.org/W2110625382","https://openalex.org/W2126203737","https://openalex.org/W2171019095","https://openalex.org/W2509065397","https://openalex.org/W2578392894","https://openalex.org/W2752782242","https://openalex.org/W2767754137","https://openalex.org/W2797583228","https://openalex.org/W2963163009","https://openalex.org/W2972613398","https://openalex.org/W2973226577","https://openalex.org/W3006926732","https://openalex.org/W3026732421","https://openalex.org/W3035524453","https://openalex.org/W3095694146","https://openalex.org/W3097777922","https://openalex.org/W3098357269","https://openalex.org/W3127242686","https://openalex.org/W3159027058","https://openalex.org/W3162273446","https://openalex.org/W3162391496","https://openalex.org/W3171975879","https://openalex.org/W3173783447","https://openalex.org/W3201143670","https://openalex.org/W3208248887","https://openalex.org/W4214493665","https://openalex.org/W4288348042","https://openalex.org/W4289243832","https://openalex.org/W4294170691","https://openalex.org/W6600593648","https://openalex.org/W6631190155","https://openalex.org/W6632978964","https://openalex.org/W6750665317","https://openalex.org/W6757022092","https://openalex.org/W6762718338","https://openalex.org/W6766978945","https://openalex.org/W6777837344","https://openalex.org/W6778102432","https://openalex.org/W6779997284","https://openalex.org/W6783944145","https://openalex.org/W6802879828","https://openalex.org/W6840487619"],"related_works":["https://openalex.org/W2114097550","https://openalex.org/W4385352507","https://openalex.org/W2918559346","https://openalex.org/W84309476","https://openalex.org/W4286904253","https://openalex.org/W2386245264","https://openalex.org/W4389912005","https://openalex.org/W4391021514","https://openalex.org/W2388033618","https://openalex.org/W1989658893"],"abstract_inverted_index":{"The":[0,62],"goal":[1],"of":[2,19,25,118,144,203,223],"keyword":[3],"spotting":[4],"(KWS)":[5],"is":[6,91,185],"to":[7,36,56,94,110,125,139,196],"find":[8],"words":[9],"and":[10,75,120,178,194,208,221],"voice":[11],"commands.":[12],"KWS":[13],"research":[14],"has":[15],"received":[16],"a":[17,46,115],"lot":[18],"attention":[20],"recently.":[21],"However,":[22],"the":[23,87,112,130,141,162,167,201,211,218],"majority":[24],"them":[26],"emphasize":[27],"predefined":[28],"KWS.":[29,152],"More":[30],"often":[31],"than":[32,187],"not,":[33],"customers":[34],"wish":[35],"choose":[37],"individualized":[38],"unique":[39],"keywords.":[40],"In":[41],"this":[42],"work,":[43],"we":[44,133],"present":[45],"brand-new":[47],"Similar-Pair":[48],"Contrastive":[49,149,197],"Learning":[50,150],"(SPCL)":[51],"training":[52,89],"method":[53],"called":[54],"MCKWS-SPCL":[55,68],"address":[57],"Multilingual":[58],"Customized":[59],"Keyword":[60],"Spotting.":[61],"three":[63],"key":[64],"processes":[65],"in":[66,84,123,151],"our":[67,145,191,224],"are":[69,107],"acoustic":[70],"feature":[71],"extraction,":[72],"embedding":[73,103],"model,":[74],"similarity":[76],"computation.":[77],"By":[78],"pushing":[79],"similar-pair":[80],"samples":[81],"closer":[82,186],"together":[83],"projection":[85],"space,":[86],"SPCL":[88,146],"approach":[90],"specifically":[92],"created":[93],"obtain":[95],"similar":[96],"features":[97],"with":[98],"noise":[99],"existing.":[100],"Additionally,":[101,200],"multiple":[102],"neural":[104],"network":[105],"structures":[106],"carefully":[108],"constructed":[109],"examine":[111],"trade-off":[113],"between":[114],"limited":[116],"number":[117],"parameters":[119],"excellent":[121],"performance":[122,143],"order":[124],"reduce":[126],"power":[127],"consumption.":[128],"For":[129],"first":[131],"time,":[132],"complete":[134],"an":[135],"all-around":[136],"multi-dimensional":[137],"comparison":[138],"demonstrate":[140,190],"superior":[142],"over":[147],"conventional":[148],"Results":[153],"from":[154],"all":[155],"trials,":[156],"including":[157],"metrics":[158],"for":[159],"average":[160],"accuracy(96.84%),":[161],"detection":[163],"error":[164],"tradeoff":[165],"curve,":[166],"false":[168,173],"reject":[169],"rate":[170,175],"under":[171],"5%":[172],"alarm":[174],"per":[176],"hour(1.901%),":[177],"visualization":[179],"using":[180],"t-Stochastic":[181],"Neighbor":[182],"Embedding(same":[183],"class":[184],"CL),":[188],"conclusively":[189],"framework's":[192],"effectiveness":[193],"superiority":[195],"Learning-based":[198],"approaches.":[199],"analysis":[202],"four":[204],"distinct":[205],"language":[206],"datasets":[207],"implementation":[209],"on":[210],"NVIDIA":[212],"JETSON":[213],"TX2":[214],"hardware":[215],"platform":[216],"demonstrates":[217],"versatility,":[219],"affordability,":[220],"hardware-friendliness":[222],"new":[225],"approach.":[226]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}