{"id":"https://openalex.org/W3008790380","doi":"https://doi.org/10.1109/asru46091.2019.9004014","title":"Query-by-Example On-Device Keyword Spotting","display_name":"Query-by-Example On-Device Keyword Spotting","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3008790380","doi":"https://doi.org/10.1109/asru46091.2019.9004014","mag":"3008790380"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9004014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9004014","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5081897616","display_name":"Byeonggeun Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Byeonggeun Kim","raw_affiliation_strings":["Qualcomm AI Research Hakdong-ro, Gangnam-gu, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm AI Research Hakdong-ro, Gangnam-gu, Seoul, Republic of Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017854079","display_name":"Mingu Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingu Lee","raw_affiliation_strings":["Qualcomm AI Research Hakdong-ro, Gangnam-gu, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm AI Research Hakdong-ro, Gangnam-gu, Seoul, Republic of Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046146264","display_name":"Jinkyu Lee","orcid":"https://orcid.org/0000-0002-2332-1996"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinkyu Lee","raw_affiliation_strings":["Qualcomm AI Research Hakdong-ro, Gangnam-gu, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm AI Research Hakdong-ro, Gangnam-gu, Seoul, Republic of Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027525808","display_name":"Yeon\u2010Seok Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yeonseok Kim","raw_affiliation_strings":["Qualcomm AI Research Hakdong-ro, Gangnam-gu, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm AI Research Hakdong-ro, Gangnam-gu, Seoul, Republic of Korea","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089149225","display_name":"Kyuwoong Hwang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kyuwoong Hwang","raw_affiliation_strings":["Qualcomm AI Research Hakdong-ro, Gangnam-gu, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm AI Research Hakdong-ro, Gangnam-gu, Seoul, Republic of Korea","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5907,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.88192504,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"532","last_page":"538"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9991999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.9136767387390137},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8567969799041748},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5643568634986877},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.543430745601654},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.5074223875999451},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48470330238342285},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4468475580215454},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4247530996799469},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3375994563102722}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9136767387390137},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8567969799041748},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5643568634986877},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.543430745601654},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.5074223875999451},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48470330238342285},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4468475580215454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4247530996799469},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3375994563102722},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.0},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru46091.2019.9004014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9004014","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8399999737739563,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1496120315","https://openalex.org/W1553469512","https://openalex.org/W1974745151","https://openalex.org/W2024490156","https://openalex.org/W2126203737","https://openalex.org/W2127141656","https://openalex.org/W2171019095","https://openalex.org/W2494980014","https://openalex.org/W2510945575","https://openalex.org/W2578392894","https://openalex.org/W2889044115","https://openalex.org/W2889176648","https://openalex.org/W2891722048","https://openalex.org/W2905970125","https://openalex.org/W2938873567","https://openalex.org/W2962707338","https://openalex.org/W2962961542","https://openalex.org/W2963414149","https://openalex.org/W2963628261","https://openalex.org/W2963881567","https://openalex.org/W2963977978","https://openalex.org/W2964187693","https://openalex.org/W2964323211","https://openalex.org/W4240592325"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W3119978414","https://openalex.org/W2114097550","https://openalex.org/W2516975559","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W4286904253","https://openalex.org/W2000885660","https://openalex.org/W1969408022","https://openalex.org/W2117995638"],"abstract_inverted_index":{"A":[0],"keyword":[1,11,104],"spotting":[2],"(KWS)":[3],"system":[4,24,30,108],"determines":[5],"the":[6,61,92,102,125,138],"existence":[7],"of,":[8],"usually":[9],"predefined,":[10],"in":[12,117,135],"a":[13,20,49,84,96],"continuous":[14],"speech":[15,52],"stream.":[16],"This":[17],"paper":[18],"presents":[19],"query-by-example":[21],"on-device":[22],"KWS":[23],"which":[25],"is":[26,70,86,121],"user-specific.":[27],"The":[28,107,119],"proposed":[29,139],"consists":[31],"of":[32,66],"two":[33,133],"main":[34],"steps:":[35],"query":[36,41,115],"enrollment":[37,42,126],"and":[38,128,137],"testing.":[39],"In":[40,82],"step,":[43],"phonetic":[44],"posteriors":[45],"are":[46],"output":[47],"by":[48,112],"small-footprint":[50],"automatic":[51],"recognition":[53],"model":[54],"based":[55,123],"on":[56,124],"connectionist":[57],"temporal":[58],"classification.":[59],"Using":[60],"phonetic-level":[62],"posteriorgram,":[63],"hypothesis":[64,105],"graph":[65],"finite-state":[67],"transducer":[68],"(FST)":[69],"built,":[71],"thus":[72,77],"can":[73],"enroll":[74],"any":[75],"keywords":[76,134],"avoiding":[78],"an":[79],"out-of-vocabulary":[80],"problem.":[81],"testing,":[83],"log-likelihood":[85],"scored":[87],"for":[88],"input":[89],"audio":[90],"using":[91,101],"FST.":[93],"We":[94,131],"propose":[95],"threshold":[97,120],"prediction":[98],"method":[99],"while":[100,144],"user-specific":[103],"only.":[106],"generates":[109],"query-specific":[110],"negatives":[111],"rearranging":[113],"each":[114],"utterance":[116],"waveform.":[118],"decided":[122],"queries":[127],"generated":[129],"negatives.":[130],"tested":[132],"English,":[136],"work":[140],"shows":[141],"promising":[142],"performance":[143],"preserving":[145],"simplicity.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}