{"id":"https://openalex.org/W4372260220","doi":"https://doi.org/10.1109/icassp49357.2023.10096596","title":"Metric Learning for User-Defined Keyword Spotting","display_name":"Metric Learning for User-Defined Keyword Spotting","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260220","doi":"https://doi.org/10.1109/icassp49357.2023.10096596"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096596","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5000060266","display_name":"Jaemin Jung","orcid":"https://orcid.org/0000-0002-6815-7763"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jaemin Jung","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,Daejeon,Republic of Korea","Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050764943","display_name":"Youkyum Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youkyum Kim","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,Daejeon,Republic of Korea","Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100740584","display_name":"Jihwan Park","orcid":"https://orcid.org/0009-0007-2223-7278"},"institutions":[{"id":"https://openalex.org/I49946491","display_name":"Hyundai Motors (South Korea)","ror":"https://ror.org/016kvft77","country_code":"KR","type":"company","lineage":["https://openalex.org/I197312522","https://openalex.org/I49946491"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jihwan Park","raw_affiliation_strings":["Hyundai Motor Company","42dot Inc., Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Hyundai Motor Company","institution_ids":["https://openalex.org/I49946491"]},{"raw_affiliation_string":"42dot Inc., Seoul, Republic of Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059677906","display_name":"Youshin Lim","orcid":"https://orcid.org/0000-0003-3328-0064"},"institutions":[{"id":"https://openalex.org/I49946491","display_name":"Hyundai Motors (South Korea)","ror":"https://ror.org/016kvft77","country_code":"KR","type":"company","lineage":["https://openalex.org/I197312522","https://openalex.org/I49946491"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youshin Lim","raw_affiliation_strings":["Hyundai Motor Company","42dot Inc., Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Hyundai Motor Company","institution_ids":["https://openalex.org/I49946491"]},{"raw_affiliation_string":"42dot Inc., Seoul, Republic of Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053784244","display_name":"Byeong-Yeol Kim","orcid":"https://orcid.org/0000-0001-6019-5047"},"institutions":[{"id":"https://openalex.org/I49946491","display_name":"Hyundai Motors (South Korea)","ror":"https://ror.org/016kvft77","country_code":"KR","type":"company","lineage":["https://openalex.org/I197312522","https://openalex.org/I49946491"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byeong-Yeol Kim","raw_affiliation_strings":["Hyundai Motor Company","42dot Inc., Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Hyundai Motor Company","institution_ids":["https://openalex.org/I49946491"]},{"raw_affiliation_string":"42dot Inc., Seoul, Republic of Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013499323","display_name":"Youngjoon Jang","orcid":"https://orcid.org/0009-0002-0500-6025"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngjoon Jang","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,Daejeon,Republic of Korea","Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"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/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,Daejeon,Republic of Korea","Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,Daejeon,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5000060266"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":2.4439,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.90938983,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9998000264167786,"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/T10860","display_name":"Speech 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/keyword-spotting","display_name":"Keyword spotting","score":0.9470233917236328},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8789842128753662},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6677682995796204},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5759372115135193},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5336291193962097},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5101109147071838},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.4865635931491852},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4791364371776581},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47591859102249146},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.46749627590179443},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4402962923049927},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39276254177093506},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33364591002464294},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33187973499298096}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9470233917236328},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8789842128753662},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6677682995796204},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5759372115135193},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5336291193962097},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5101109147071838},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.4865635931491852},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4791364371776581},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47591859102249146},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.46749627590179443},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4402962923049927},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39276254177093506},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33364591002464294},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33187973499298096},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096596","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096596","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2096733369","https://openalex.org/W2187089797","https://openalex.org/W2219249508","https://openalex.org/W2407023693","https://openalex.org/W2555897561","https://openalex.org/W2601450892","https://openalex.org/W2747874407","https://openalex.org/W2769912137","https://openalex.org/W2784163702","https://openalex.org/W2797583228","https://openalex.org/W2808631503","https://openalex.org/W2899771611","https://openalex.org/W2962788625","https://openalex.org/W2962898354","https://openalex.org/W2963386851","https://openalex.org/W2963839617","https://openalex.org/W2964187693","https://openalex.org/W2973226577","https://openalex.org/W3013020904","https://openalex.org/W3030437843","https://openalex.org/W3036601975","https://openalex.org/W3037988796","https://openalex.org/W3046052470","https://openalex.org/W3103152812","https://openalex.org/W3139329035","https://openalex.org/W3144247233","https://openalex.org/W3148564648","https://openalex.org/W3162273446","https://openalex.org/W3163505255","https://openalex.org/W3196496149","https://openalex.org/W3197564965","https://openalex.org/W3198035615","https://openalex.org/W6631190155","https://openalex.org/W6688816777","https://openalex.org/W6730323794","https://openalex.org/W6735236233","https://openalex.org/W6746451879","https://openalex.org/W6750665317","https://openalex.org/W6756040250","https://openalex.org/W6771467084","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W3119978414","https://openalex.org/W2114097550","https://openalex.org/W2516975559","https://openalex.org/W3206647229","https://openalex.org/W4286904253","https://openalex.org/W2000885660","https://openalex.org/W1969408022","https://openalex.org/W2117995638","https://openalex.org/W1989658893"],"abstract_inverted_index":{"The":[0,34],"goal":[1],"of":[2,44],"this":[3,27,47],"work":[4],"is":[5],"to":[6,31,36,84,120],"detect":[7],"new":[8],"spoken":[9],"terms":[10,43],"defined":[11],"by":[12,115,153],"users.":[13],"While":[14],"most":[15],"previous":[16,151],"works":[17,152],"address":[18],"Keyword":[19],"Spotting":[20],"(KWS)":[21],"as":[22,166,168],"a":[23,51,70,81,94,154],"closed-set":[24],"classification":[25],"problem,":[26],"limits":[28],"their":[29,117],"transferability":[30],"unseen":[32],"terms.":[33],"ability":[35],"define":[37],"custom":[38],"keywords":[39],"has":[40],"advantages":[41],"in":[42,125],"user":[45],"experience.In":[46],"paper,":[48],"we":[49,62,68,92,130],"propose":[50,80,93,131],"metric":[52,95],"learning-based":[53,96],"training":[54,98,144],"strategy":[55],"for":[56],"user-defined":[57,111,127,147],"keyword":[58,72,112],"spotting.":[59],"In":[60],"particular,":[61],"make":[63],"the":[64,103,107,110,122,126,146,158,164,169],"following":[65],"contributions:":[66],"(1)":[67],"construct":[69],"large-scale":[71],"dataset":[73,162],"with":[74],"an":[75,142],"existing":[76,170],"speech":[77],"corpus":[78],"and":[79,100,135,149],"filtering":[82],"method":[83,105],"remove":[85],"data":[86],"that":[87,102],"degrade":[88],"model":[89],"training;":[90],"(2)":[91],"two-stage":[97],"strategy,":[99],"demonstrate":[101],"proposed":[104,137,165],"improves":[106],"performance":[108],"on":[109,145,157],"spotting":[113],"task":[114],"enriching":[116],"representations;":[118],"(3)":[119],"facilitate":[121],"fair":[123],"comparison":[124],"KWS":[128],"field,":[129],"unified":[132],"evaluation":[133],"protocol":[134],"metrics.Our":[136],"system":[138],"does":[139],"not":[140],"require":[141],"incremental":[143],"keywords,":[148],"outperforms":[150],"significant":[155],"margin":[156],"Google":[159],"Speech":[160],"Commands":[161],"using":[163],"well":[167],"metrics.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}