{"id":"https://openalex.org/W4319862284","doi":"https://doi.org/10.1109/slt54892.2023.10022851","title":"Fully Unsupervised Training of Few-Shot Keyword Spotting","display_name":"Fully Unsupervised Training of Few-Shot Keyword Spotting","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862284","doi":"https://doi.org/10.1109/slt54892.2023.10022851"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022851","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022851","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5040382938","display_name":"Dongjune Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dongjune Lee","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea","Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027616639","display_name":"Minchan Kim","orcid":"https://orcid.org/0000-0002-8150-765X"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minchan Kim","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea","Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061659301","display_name":"Sung Hwan Mun","orcid":"https://orcid.org/0000-0003-2554-8294"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sung Hwan Mun","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea","Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009851092","display_name":"Min Hyun Han","orcid":"https://orcid.org/0000-0002-8086-5009"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Min Hyun Han","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea","Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051356511","display_name":"Nam Soo Kim","orcid":"https://orcid.org/0000-0002-0568-4902"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nam Soo Kim","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea","Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"266","last_page":"272"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9954000115394592,"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":0.9948999881744385,"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":0.9053298234939575},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.850562334060669},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6939474940299988},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.691681444644928},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6431636214256287},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4591900408267975},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.43144360184669495},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4042150378227234},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37154918909072876},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3369414210319519},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3210670053958893}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9053298234939575},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.850562334060669},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6939474940299988},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.691681444644928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6431636214256287},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4591900408267975},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.43144360184669495},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4042150378227234},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37154918909072876},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3369414210319519},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3210670053958893},{"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022851","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022851","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4394283675","display_name":null,"funder_award_id":"2021-0-00456","funder_id":"https://openalex.org/F4320324891","funder_display_name":"Iran Telecommunication Research Center"}],"funders":[{"id":"https://openalex.org/F4320324891","display_name":"Iran Telecommunication Research Center","ror":"https://ror.org/01a3g2z22"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2219249508","https://openalex.org/W2696967604","https://openalex.org/W2797583228","https://openalex.org/W2905970125","https://openalex.org/W2963775347","https://openalex.org/W2972613398","https://openalex.org/W2973034126","https://openalex.org/W2973226577","https://openalex.org/W3011199201","https://openalex.org/W3015399080","https://openalex.org/W3025581723","https://openalex.org/W3046052470","https://openalex.org/W3095410713","https://openalex.org/W3144247233","https://openalex.org/W3148564648","https://openalex.org/W3196496149","https://openalex.org/W3198035615","https://openalex.org/W3208049241","https://openalex.org/W4212774754","https://openalex.org/W4221166168","https://openalex.org/W4283730082","https://openalex.org/W4283767777","https://openalex.org/W4287122539","https://openalex.org/W6688816777","https://openalex.org/W6750665317","https://openalex.org/W6757015787","https://openalex.org/W6780218876","https://openalex.org/W6796464841","https://openalex.org/W6797053846","https://openalex.org/W6800638362"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W3119978414","https://openalex.org/W2114097550","https://openalex.org/W2545741539","https://openalex.org/W2516975559","https://openalex.org/W3206647229","https://openalex.org/W4286904253","https://openalex.org/W2000885660","https://openalex.org/W1969408022","https://openalex.org/W1989658893"],"abstract_inverted_index":{"For":[0],"training":[1],"a":[2,8,29,46,89],"few-shot":[3],"keyword":[4],"spotting":[5],"(FS-KWS)":[6],"model,":[7],"large":[9,90],"labeled":[10,112,144],"dataset":[11],"containing":[12],"massive":[13],"target":[14,25,64],"keywords":[15,26,65],"has":[16],"known":[17],"to":[18,21,23,66],"be":[19,67],"essential":[20],"generalize":[22],"arbitrary":[24],"with":[27,39,80,95],"only":[28,51],"few":[30],"enrollment":[31],"samples.":[32],"To":[33],"alleviate":[34],"the":[35,73,96,116],"expensive":[36],"data":[37],"collection":[38,91],"labeling,":[40],"in":[41,118],"this":[42],"paper,":[43],"we":[44,86],"propose":[45],"novel":[47],"FS-KWS":[48],"system":[49,57],"trained":[50],"on":[52,60,132],"synthetic":[53],"data.":[54,113],"The":[55],"proposed":[56,137],"is":[58,139],"based":[59],"metric":[61,106],"learning":[62,107],"enabling":[63],"detected":[68],"using":[69],"distance":[70],"metrics.":[71],"Exploiting":[72],"speech":[74,79],"synthesis":[75],"model":[76],"that":[77],"generates":[78],"pseudo":[81],"phonemes":[82],"instead":[83],"of":[84,92,115],"texts,":[85],"easily":[87],"obtain":[88],"multi-view":[93],"samples":[94,100],"same":[97],"semantics.":[98],"These":[99],"are":[101],"sufficient":[102],"for":[103],"training,":[104],"considering":[105],"does":[108],"not":[109,122],"intrinsically":[110],"necessitate":[111],"All":[114],"components":[117],"our":[119,127,136],"framework":[120],"do":[121],"require":[123],"any":[124,143],"supervision,":[125],"making":[126],"method":[128,138],"unsupervised.":[129],"Experimental":[130],"results":[131],"real":[133,146],"datasets":[134],"show":[135],"competitive":[140],"even":[141],"without":[142],"and":[145],"datasets.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}