{"id":"https://openalex.org/W3163571828","doi":"https://doi.org/10.1109/access.2021.3078715","title":"Wav2KWS: Transfer Learning From Speech Representations for Keyword Spotting","display_name":"Wav2KWS: Transfer Learning From Speech Representations for Keyword Spotting","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3163571828","doi":"https://doi.org/10.1109/access.2021.3078715","mag":"3163571828"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3078715","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3078715","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09427206.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09427206.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082621198","display_name":"Deokjin Seo","orcid":"https://orcid.org/0000-0002-3760-9616"},"institutions":[{"id":"https://openalex.org/I113409471","display_name":"Kumoh National Institute of Technology","ror":"https://ror.org/05dkjfz60","country_code":"KR","type":"education","lineage":["https://openalex.org/I113409471"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Deokjin Seo","raw_affiliation_strings":["Department of Computer Engineering, Kumoh National Institute of Technology (KIT), Gumi, South Korea","Kumoh National Institute of Technology (KIT), Gumi, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Kumoh National Institute of Technology (KIT), Gumi, South Korea","institution_ids":["https://openalex.org/I113409471"]},{"raw_affiliation_string":"Kumoh National Institute of Technology (KIT), Gumi, South Korea","institution_ids":["https://openalex.org/I113409471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014007202","display_name":"Heung\u2010Seon Oh","orcid":"https://orcid.org/0000-0002-9193-8998"},"institutions":[{"id":"https://openalex.org/I35886859","display_name":"Korea University of Technology and Education","ror":"https://ror.org/053nycv62","country_code":"KR","type":"education","lineage":["https://openalex.org/I35886859"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Heung-Seon Oh","raw_affiliation_strings":["School of Computer Science and Engineering, Korea University of Technology and Education (KOREATECH), Cheonan, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-9193-8998","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Korea University of Technology and Education (KOREATECH), Cheonan, South Korea","institution_ids":["https://openalex.org/I35886859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068355358","display_name":"Yuchul Jung","orcid":"https://orcid.org/0000-0002-8871-1979"},"institutions":[{"id":"https://openalex.org/I113409471","display_name":"Kumoh National Institute of Technology","ror":"https://ror.org/05dkjfz60","country_code":"KR","type":"education","lineage":["https://openalex.org/I113409471"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yuchul Jung","raw_affiliation_strings":["Department of Computer Engineering, Kumoh National Institute of Technology (KIT), Gumi, South Korea","Kumoh National Institute of Technology (KIT), Gumi, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-8871-1979","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Kumoh National Institute of Technology (KIT), Gumi, South Korea","institution_ids":["https://openalex.org/I113409471"]},{"raw_affiliation_string":"Kumoh National Institute of Technology (KIT), Gumi, South Korea","institution_ids":["https://openalex.org/I113409471"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":5.6334,"has_fulltext":true,"cited_by_count":50,"citation_normalized_percentile":{"value":0.96567606,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"9","issue":null,"first_page":"80682","last_page":"80691"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.9991000294685364,"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":0.9568028450012207},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8908500671386719},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5706785917282104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5385575890541077},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5275770425796509},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5113953948020935},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44965410232543945},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4425009787082672},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4347579777240753},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4214346408843994},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3443560302257538}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9568028450012207},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8908500671386719},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5706785917282104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5385575890541077},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5275770425796509},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5113953948020935},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44965410232543945},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4425009787082672},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4347579777240753},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4214346408843994},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3443560302257538},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2021.3078715","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3078715","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09427206.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:df2fdc49d44e4baf8fbfba430351bbdb","is_oa":true,"landing_page_url":"https://doaj.org/article/df2fdc49d44e4baf8fbfba430351bbdb","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 9, Pp 80682-80691 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3078715","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3078715","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09427206.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5199999809265137,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G158386941","display_name":null,"funder_award_id":"P0006704","funder_id":"https://openalex.org/F4320321681","funder_display_name":"Ministry of Trade, Industry and Energy"},{"id":"https://openalex.org/G3461382341","display_name":null,"funder_award_id":"NRF-2018R1C1B5031408","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G4989225994","display_name":null,"funder_award_id":"P0006704","funder_id":"https://openalex.org/F4320322064","funder_display_name":"Korea Institute for Advancement of Technology"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320321260","display_name":"Korea University of Technology and Education","ror":"https://ror.org/053nycv62"},{"id":"https://openalex.org/F4320321373","display_name":"Korea University","ror":"https://ror.org/047dqcg40"},{"id":"https://openalex.org/F4320321681","display_name":"Ministry of Trade, Industry and Energy","ror":"https://ror.org/008nkqk13"},{"id":"https://openalex.org/F4320322064","display_name":"Korea Institute for Advancement of Technology","ror":"https://ror.org/015w1qa96"},{"id":"https://openalex.org/F4320322065","display_name":"National IT Industry Promotion Agency","ror":"https://ror.org/026v53e29"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3163571828.pdf","grobid_xml":"https://content.openalex.org/works/W3163571828.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2034940213","https://openalex.org/W2124509324","https://openalex.org/W2149933564","https://openalex.org/W2193413348","https://openalex.org/W2327501763","https://openalex.org/W2507580616","https://openalex.org/W2602634800","https://openalex.org/W2748659049","https://openalex.org/W2769912137","https://openalex.org/W2797527871","https://openalex.org/W2797583228","https://openalex.org/W2888641632","https://openalex.org/W2889511491","https://openalex.org/W2896457183","https://openalex.org/W2899663614","https://openalex.org/W2910655080","https://openalex.org/W2930364467","https://openalex.org/W2936774411","https://openalex.org/W2953219395","https://openalex.org/W2961149267","https://openalex.org/W2963159690","https://openalex.org/W2963323070","https://openalex.org/W2963341956","https://openalex.org/W2963748441","https://openalex.org/W2964121744","https://openalex.org/W2964187693","https://openalex.org/W2973049979","https://openalex.org/W2973226577","https://openalex.org/W2998589588","https://openalex.org/W3013571468","https://openalex.org/W3015399080","https://openalex.org/W3015537910","https://openalex.org/W3017216675","https://openalex.org/W3021469861","https://openalex.org/W3025581723","https://openalex.org/W3026041220","https://openalex.org/W3081469894","https://openalex.org/W3093579165","https://openalex.org/W3095173472","https://openalex.org/W3095838132","https://openalex.org/W3097018422","https://openalex.org/W3104334086","https://openalex.org/W3148040514","https://openalex.org/W4287824654","https://openalex.org/W4299518610","https://openalex.org/W6631190155","https://openalex.org/W6682132143","https://openalex.org/W6687566353","https://openalex.org/W6746451879","https://openalex.org/W6750665317","https://openalex.org/W6750963839","https://openalex.org/W6755207826","https://openalex.org/W6755977528","https://openalex.org/W6765779497","https://openalex.org/W6771917389","https://openalex.org/W6772781875","https://openalex.org/W6782875283","https://openalex.org/W6784614252"],"related_works":["https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W1909292483","https://openalex.org/W1428730622","https://openalex.org/W1658560081","https://openalex.org/W2146616055","https://openalex.org/W2899676847","https://openalex.org/W596245619","https://openalex.org/W2254895521"],"abstract_inverted_index":{"With":[0],"the":[1,76,90,93,112,115,142],"expanding":[2],"development":[3],"of":[4,92,114],"on-device":[5,17],"artificial":[6],"intelligence,":[7],"voice-enabled":[8],"devices":[9],"such":[10],"as":[11,75],"smart":[12],"speakers,":[13],"wearables,":[14],"and":[15,79,106],"other":[16],"or":[18,27],"edge":[19],"processing":[20],"systems":[21],"have":[22],"been":[23],"proposed.":[24],"However,":[25],"building":[26],"obtaining":[28],"large":[29],"training":[30],"datasets":[31],"that":[32,52],"are":[33],"essential":[34],"for":[35,86,117],"robust":[36],"keyword":[37,62],"spotting":[38],"(KWS)":[39],"remains":[40],"cumbersome.":[41],"To":[42,88],"address":[43],"this":[44],"problem,":[45],"we":[46,120],"propose":[47],"a":[48,56,71],"deep":[49,135],"neural":[50,136],"network":[51,78,85,116,132,144],"can":[53,145],"rapidly":[54],"establish":[55],"high-performance":[57],"KWS":[58],"system":[59],"from":[60],"arbitrary":[61],"instruction":[63],"sets.":[64],"We":[65],"use":[66],"an":[67,82],"encoder":[68],"pretrained":[69],"with":[70,153],"large-scale":[72],"speech":[73,127],"corpus":[74],"backbone":[77],"then":[80],"design":[81],"effective":[83],"transfer":[84],"KWS.":[87],"demonstrate":[89],"feasibility":[91],"proposed":[94,131,143],"network,":[95],"various":[96],"experiments":[97,122],"were":[98],"conducted":[99,121],"on":[100],"Google":[101],"Speech":[102],"Command":[103],"Datasets":[104],"V1":[105],"V2.":[107],"In":[108],"addition,":[109],"to":[110],"verify":[111],"applicability":[113],"different":[118,125],"languages,":[119],"using":[123],"three":[124],"Korean":[126],"command":[128],"datasets.":[129],"The":[130],"outperforms":[133],"state-of-the-art":[134],"networks":[137],"in":[138],"both":[139],"experiments.":[140],"Furthermore,":[141],"understand":[146],"real":[147],"human":[148],"voice":[149],"even":[150],"when":[151],"trained":[152],"synthetic":[154],"text-to-speech":[155],"data.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-01T08:55:40.977307","created_date":"2025-10-10T00:00:00"}