{"id":"https://openalex.org/W4406462000","doi":"https://doi.org/10.1109/slt61566.2024.10832206","title":"GE2E-KWS: Generalized End-to-End Training and Evaluation for Zero-Shot Keyword Spotting","display_name":"GE2E-KWS: Generalized End-to-End Training and Evaluation for Zero-Shot Keyword Spotting","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406462000","doi":"https://doi.org/10.1109/slt61566.2024.10832206"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832206","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5053897661","display_name":"Pai Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Pai Zhu","raw_affiliation_strings":["Google LLC, Mountain View,CA,U.S.A"],"affiliations":[{"raw_affiliation_string":"Google LLC, Mountain View,CA,U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022305901","display_name":"Jacob Bartel","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob W. Bartel","raw_affiliation_strings":["Google LLC, Mountain View,CA,U.S.A"],"affiliations":[{"raw_affiliation_string":"Google LLC, Mountain View,CA,U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109792797","display_name":"Dhruuv Agarwal","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhruuv Agarwal","raw_affiliation_strings":["Google LLC, Mountain View,CA,U.S.A"],"affiliations":[{"raw_affiliation_string":"Google LLC, Mountain View,CA,U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029221117","display_name":"Kurt Partridge","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kurt Partridge","raw_affiliation_strings":["Google LLC, Mountain View,CA,U.S.A"],"affiliations":[{"raw_affiliation_string":"Google LLC, Mountain View,CA,U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101720007","display_name":"Hyun Jin Park","orcid":"https://orcid.org/0000-0001-7062-0414"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyun Jin Park","raw_affiliation_strings":["Google LLC, Mountain View,CA,U.S.A"],"affiliations":[{"raw_affiliation_string":"Google LLC, Mountain View,CA,U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111346142","display_name":"Quan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Quan Wang","raw_affiliation_strings":["Google LLC, Mountain View,CA,U.S.A"],"affiliations":[{"raw_affiliation_string":"Google LLC, Mountain View,CA,U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5053897661"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23190269,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"999","last_page":"1006"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9980999827384949,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9980999827384949,"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":0.9973000288009644,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9962999820709229,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.8288086652755737},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7281734943389893},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.6800732612609863},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6257106065750122},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.613861083984375},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5948532819747925},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4833676218986511},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4799545109272003},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41057324409484863},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06277114152908325},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.054847508668899536}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.8288086652755737},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7281734943389893},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.6800732612609863},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6257106065750122},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.613861083984375},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5948532819747925},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4833676218986511},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4799545109272003},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41057324409484863},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06277114152908325},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.054847508668899536},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832206","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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":28,"referenced_works":["https://openalex.org/W2004409624","https://openalex.org/W2024490156","https://openalex.org/W2034940213","https://openalex.org/W2064675550","https://openalex.org/W2096733369","https://openalex.org/W2747238065","https://openalex.org/W2797583228","https://openalex.org/W2886006657","https://openalex.org/W2928941594","https://openalex.org/W2962788625","https://openalex.org/W2963702081","https://openalex.org/W2963977978","https://openalex.org/W2972613398","https://openalex.org/W3015399080","https://openalex.org/W3025581723","https://openalex.org/W3097777922","https://openalex.org/W3198035615","https://openalex.org/W4206567542","https://openalex.org/W4224916413","https://openalex.org/W4284888338","https://openalex.org/W4297677272","https://openalex.org/W4375869070","https://openalex.org/W4381786045","https://openalex.org/W4392903365","https://openalex.org/W4392904087","https://openalex.org/W6750665317","https://openalex.org/W6760633627","https://openalex.org/W6800638362"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W4286904253","https://openalex.org/W3119978414","https://openalex.org/W2516975559","https://openalex.org/W3206647229","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2545741539","https://openalex.org/W1989658893"],"abstract_inverted_index":{"We":[0],"propose":[1,72],"GE2E-KWS\u2014a":[2],"generalized":[3],"end-to-end":[4],"training":[5,24,54],"and":[6,18,26,46,49,53,81,109,130],"evaluation":[7,74],"framework":[8],"for":[9,140],"customized":[10],"keyword":[11,87],"spotting.":[12],"Specifically,":[13],"enrollment":[14,45],"utterances":[15],"are":[16,30,123],"separated":[17],"grouped":[19],"by":[20,56,105,117],"keywords":[21,142],"from":[22],"the":[23,40,78],"batch":[25],"their":[27],"embedding":[28],"centroids":[29],"compared":[31,60],"to":[32,38,61,132],"all":[33],"other":[34],"test":[35],"utterance":[36],"embeddings":[37],"compute":[39,82],"loss.":[41],"This":[42],"simulates":[43],"runtime":[44],"verification":[47],"stages,":[48],"improves":[50],"convergence":[51],"stability":[52],"speed":[55],"optimizing":[57],"matrix":[58],"operations":[59],"SOTA":[62],"triplet":[63,114],"loss":[64,115],"approaches.":[65],"To":[66],"benchmark":[67],"different":[68],"models":[69,122],"reliably,":[70],"we":[71],"an":[73],"process":[75],"that":[76,84],"mimics":[77],"production":[79],"environment":[80],"metrics":[83],"directly":[85],"measure":[86],"matching":[88],"accuracy.":[89],"Trained":[90],"with":[91,126,136],"GE2E":[92],"loss,":[93],"our":[94],"419KB":[95],"quantized":[96],"conformer":[97],"model":[98,116],"beats":[99,110],"a":[100,111],"7.5":[101],"GB":[102],"ASR":[103],"encoder":[104],"23.6%":[106],"relative":[107],"AUC,":[108],"same":[112],"size":[113],"60.7%":[118],"AUC.":[119],"Our":[120],"KWS":[121],"natively":[124],"streamable":[125],"low":[127],"memory":[128],"footprints,":[129],"designed":[131],"continuously":[133],"run":[134],"on-device":[135],"no":[137],"retraining":[138],"needed":[139],"new":[141],"(zero-shot).":[143]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}