{"id":"https://openalex.org/W3162273446","doi":"https://doi.org/10.1109/icassp39728.2021.9414156","title":"Query-By-Example Keyword Spotting System Using Multi-Head Attention and Soft-triple Loss","display_name":"Query-By-Example Keyword Spotting System Using Multi-Head Attention and Soft-triple Loss","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162273446","doi":"https://doi.org/10.1109/icassp39728.2021.9414156","mag":"3162273446"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5062106974","display_name":"Jinmiao Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jinmiao Huang","raw_affiliation_strings":["Toronto AI Lab, LG Electronics, Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"Toronto AI Lab, LG Electronics, Toronto, Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051092022","display_name":"Waseem Gharbieh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Waseem Gharbieh","raw_affiliation_strings":["Toronto AI Lab, LG Electronics, Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"Toronto AI Lab, LG Electronics, Toronto, Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025143578","display_name":"Han Suk Shim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han Suk Shim","raw_affiliation_strings":["Artificial Intelligence Lab, LG Electronics, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Lab, LG Electronics, Seoul, Korea","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341135","display_name":"Eugene Kim","orcid":"https://orcid.org/0000-0001-9004-2527"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eugene Kim","raw_affiliation_strings":["Artificial Intelligence Lab, LG Electronics, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Lab, LG Electronics, Seoul, Korea","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5062106974"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2632,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.93192481,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6858","last_page":"6862"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9986000061035156,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9986000061035156,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9986000061035156,"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":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.8664971590042114},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.8189144730567932},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.6607074737548828},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6050761938095093},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5186452269554138},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.5137237310409546},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4962337613105774},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.445210337638855},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.4326038062572479},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4220535159111023},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.36825305223464966},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34144824743270874},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33418697118759155}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8664971590042114},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.8189144730567932},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.6607074737548828},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6050761938095093},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5186452269554138},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.5137237310409546},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4962337613105774},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.445210337638855},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.4326038062572479},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4220535159111023},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.36825305223464966},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34144824743270874},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33418697118759155},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/icassp39728.2021.9414156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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":25,"referenced_works":["https://openalex.org/W114193738","https://openalex.org/W1494198834","https://openalex.org/W1496120315","https://openalex.org/W2034940213","https://openalex.org/W2126203737","https://openalex.org/W2171019095","https://openalex.org/W2578392894","https://openalex.org/W2598634450","https://openalex.org/W2747874407","https://openalex.org/W2902773438","https://openalex.org/W2951974815","https://openalex.org/W2962707338","https://openalex.org/W2962736743","https://openalex.org/W2962959915","https://openalex.org/W2963403868","https://openalex.org/W2963628261","https://openalex.org/W2963879374","https://openalex.org/W2964187693","https://openalex.org/W2991234496","https://openalex.org/W4289243832","https://openalex.org/W4385245566","https://openalex.org/W6604666349","https://openalex.org/W6735531217","https://openalex.org/W6739901393","https://openalex.org/W6757022092"],"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":{"This":[0],"paper":[1],"proposes":[2],"a":[3,24,32,49,88],"neural":[4],"network":[5],"architecture":[6],"for":[7,27,39],"tackling":[8],"the":[9,45,64,76,82,99],"query-by-example":[10],"user-defined":[11],"keyword":[12],"spotting":[13],"task.":[14],"A":[15],"multi-head":[16,34],"attention":[17,35],"module":[18,36],"is":[19,37],"added":[20],"on":[21,69],"top":[22],"of":[23,51,66,84,101],"multi-layered":[25],"GRU":[26],"effective":[28],"feature":[29,40],"extraction,":[30],"and":[31,54,58,75,92],"normalized":[33],"proposed":[38,108],"aggregation.":[41],"We":[42,62,80],"also":[43],"adopt":[44],"softtriple":[46],"loss":[47,53,56],"-":[48,57],"combination":[50],"triplet":[52],"softmax":[55],"showcase":[59],"its":[60],"effectiveness.":[61],"demonstrate":[63],"performance":[65,83,112],"our":[67,85,105],"model":[68,86],"internal":[70],"datasets":[71],"with":[72],"different":[73],"languages":[74],"public":[77],"Hey-Snips":[78],"dataset.":[79],"compare":[81],"to":[87,97],"baseline":[89],"system":[90],"[1]":[91],"conduct":[93],"an":[94],"ablation":[95],"study":[96],"show":[98],"benefit":[100],"each":[102],"component":[103],"in":[104],"architecture.":[106],"The":[107],"work":[109],"shows":[110],"solid":[111],"while":[113],"preserving":[114],"simplicity.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}