{"id":"https://openalex.org/W3024903177","doi":"https://doi.org/10.1109/slt48900.2021.9383571","title":"Metric Learning for Keyword Spotting","display_name":"Metric Learning for Keyword Spotting","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3024903177","doi":"https://doi.org/10.1109/slt48900.2021.9383571","mag":"3024903177"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383571","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383571","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2005.08776","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114067866","display_name":"Jaesung Huh","orcid":"https://orcid.org/0000-0001-7247-6401"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]},{"id":"https://openalex.org/I2802123492","display_name":"Oxford Research Group","ror":"https://ror.org/00z4w4f29","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802123492"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jaesung Huh","raw_affiliation_strings":["Visual Geometry Group, University of Oxford, UK","NAVER CORPORATION"],"affiliations":[{"raw_affiliation_string":"Visual Geometry Group, University of Oxford, UK","institution_ids":["https://openalex.org/I2802123492","https://openalex.org/I40120149"]},{"raw_affiliation_string":"NAVER CORPORATION","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100449738","display_name":"Minjae Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minjae Lee","raw_affiliation_strings":["Naver Corporation, South Korea","NAVER CORPORATION"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"NAVER CORPORATION","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070613375","display_name":"Hee-Soo Heo","orcid":"https://orcid.org/0000-0003-1567-123X"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Heesoo Heo","raw_affiliation_strings":["Naver Corporation, South Korea","NAVER CORPORATION"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"NAVER CORPORATION","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021831317","display_name":"Seongkyu Mun","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seongkyu Mun","raw_affiliation_strings":["Naver Corporation, South Korea","NAVER CORPORATION"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"NAVER CORPORATION","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["Naver Corporation, South Korea","NAVER CORPORATION"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"NAVER CORPORATION","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5114067866"],"corresponding_institution_ids":["https://openalex.org/I2802123492","https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00409478,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"133","last_page":"140"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.8930065631866455},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.8807905912399292},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7949100732803345},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.656827449798584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.615270733833313},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6100841760635376},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47139623761177063},{"id":"https://openalex.org/keywords/false-alarm","display_name":"False alarm","score":0.45863616466522217},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44298192858695984},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3356027901172638}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.8930065631866455},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.8807905912399292},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7949100732803345},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.656827449798584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.615270733833313},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6100841760635376},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47139623761177063},{"id":"https://openalex.org/C2776836416","wikidata":"https://www.wikidata.org/wiki/Q1364844","display_name":"False alarm","level":2,"score":0.45863616466522217},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44298192858695984},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3356027901172638},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/slt48900.2021.9383571","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383571","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2005.08776","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.08776","pdf_url":"https://arxiv.org/pdf/2005.08776","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3024903177","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2005.08776","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2005.08776","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2005.08776","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/f1va-hk65","is_oa":true,"landing_page_url":"https://doi.org/10.17023/f1va-hk65","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2005.08776","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.08776","pdf_url":"https://arxiv.org/pdf/2005.08776","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3024903177.pdf"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1532499126","https://openalex.org/W1582774210","https://openalex.org/W1618905105","https://openalex.org/W1875842236","https://openalex.org/W1983205135","https://openalex.org/W2034940213","https://openalex.org/W2096733369","https://openalex.org/W2141354973","https://openalex.org/W2153635508","https://openalex.org/W2157364932","https://openalex.org/W2194775991","https://openalex.org/W2325939864","https://openalex.org/W2407023693","https://openalex.org/W2510216776","https://openalex.org/W2587529061","https://openalex.org/W2601450892","https://openalex.org/W2726515241","https://openalex.org/W2747238065","https://openalex.org/W2762466393","https://openalex.org/W2769912137","https://openalex.org/W2797583228","https://openalex.org/W2798405286","https://openalex.org/W2898867055","https://openalex.org/W2899771611","https://openalex.org/W2910655080","https://openalex.org/W2930364467","https://openalex.org/W2949117887","https://openalex.org/W2955961252","https://openalex.org/W2962788625","https://openalex.org/W2963628261","https://openalex.org/W2963775347","https://openalex.org/W2963840672","https://openalex.org/W2964187693","https://openalex.org/W2969335882","https://openalex.org/W2973149080","https://openalex.org/W2973226577","https://openalex.org/W3013020904","https://openalex.org/W3015287265","https://openalex.org/W3019293601","https://openalex.org/W3091905774","https://openalex.org/W3099206234","https://openalex.org/W4254751698","https://openalex.org/W6631190155","https://openalex.org/W6631637103","https://openalex.org/W6636501900","https://openalex.org/W6638667902","https://openalex.org/W6675354045","https://openalex.org/W6681151457","https://openalex.org/W6683390034","https://openalex.org/W6696085341","https://openalex.org/W6700903540","https://openalex.org/W6735236233","https://openalex.org/W6746451879","https://openalex.org/W6750665317","https://openalex.org/W6756040250","https://openalex.org/W6757015787","https://openalex.org/W6757472134","https://openalex.org/W6766978945","https://openalex.org/W6781011824","https://openalex.org/W6783596713"],"related_works":["https://openalex.org/W2905115762","https://openalex.org/W3206276570","https://openalex.org/W2783822844","https://openalex.org/W3158819498","https://openalex.org/W3014859249","https://openalex.org/W2003699243","https://openalex.org/W3180805579","https://openalex.org/W2918598763","https://openalex.org/W2187579920","https://openalex.org/W3128745314","https://openalex.org/W2774752028","https://openalex.org/W2961917444","https://openalex.org/W2289324734","https://openalex.org/W3176777339","https://openalex.org/W2735253541","https://openalex.org/W3016958856","https://openalex.org/W2761188821","https://openalex.org/W2902488667","https://openalex.org/W2914805075","https://openalex.org/W2798991696"],"abstract_inverted_index":{"The":[0],"goal":[1],"of":[2,78],"this":[3,119],"work":[4],"is":[5,65,109],"to":[6,85,166],"train":[7],"effective":[8],"representations":[9],"for":[10,144],"keyword":[11,20,38,63],"spotting":[12,21,64],"via":[13],"metric":[14,86,128],"learning.":[15],"Most":[16],"existing":[17],"works":[18],"address":[19],"as":[22,147],"a":[23,66,76,106,123],"closed-set":[24],"classification":[25,149,174],"problem,":[26],"where":[27,69],"both":[28],"target":[29,71,103,112,135,145],"and":[30,93,116,136],"non-target":[31,44,95,137,168],"keywords":[32,72,113,146],"are":[33,47,73,114],"predefined.":[34,117],"Therefore,":[35],"prevailing":[36],"classifier-based":[37],"spot-ting":[39],"systems":[40],"perform":[41],"poorly":[42],"on":[43,127,152],"sounds":[45,96],"which":[46],"unseen":[48,92,167],"during":[49],"the":[50,91,102,111,132,153,172],"training":[51],"stage,":[52],"causing":[53],"high":[54],"false":[55,164],"alarm":[56],"rates":[57],"in":[58,89,148],"real-world":[59],"scenarios.":[60],"In":[61],"reality,":[62],"detection":[67],"problem":[68],"predefined":[70],"detected":[74],"from":[75,101],"variety":[77],"unknown":[79,94],"sounds.":[80],"This":[81],"shares":[82],"many":[83],"similarities":[84],"learning":[87,129],"problems":[88],"that":[90,110,130,159],"must":[97],"be":[98],"clearly":[99],"differentiated":[100],"keywords.":[104],"However,":[105],"key":[107],"difference":[108],"known":[115],"To":[118],"end,":[120],"we":[121],"propose":[122],"new":[124],"method":[125,161],"based":[126],"maximises":[131],"distance":[133],"between":[134],"key-words,":[138],"but":[139],"also":[140],"learns":[141],"per-class":[142],"weights":[143],"objectives.":[150],"Experiments":[151],"Google":[154],"Speech":[155],"Commands":[156],"dataset":[157],"show":[158],"our":[160],"significantly":[162],"reduces":[163],"alarms":[165],"keywords,":[169],"while":[170],"maintaining":[171],"overall":[173],"accuracy.":[175]},"counts_by_year":[],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}