{"id":"https://openalex.org/W3012505451","doi":"https://doi.org/10.1109/icassp40776.2020.9053313","title":"Towards Data-Efficient Modeling for Wake Word Spotting","display_name":"Towards Data-Efficient Modeling for Wake Word Spotting","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3012505451","doi":"https://doi.org/10.1109/icassp40776.2020.9053313","mag":"3012505451"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053313","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053313","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5101781558","display_name":"Yixin Gao","orcid":"https://orcid.org/0000-0001-8854-8959"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yixin Gao","raw_affiliation_strings":["Alexa, Amazon.com Inc, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Alexa, Amazon.com Inc, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041625765","display_name":"Yuriy Mishchenko","orcid":"https://orcid.org/0009-0006-0826-5777"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuriy Mishchenko","raw_affiliation_strings":["Alexa, Amazon.com Inc, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Alexa, Amazon.com Inc, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071440743","display_name":"Anish Shah","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anish Shah","raw_affiliation_strings":["Alexa, Amazon.com Inc, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Alexa, Amazon.com Inc, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034173999","display_name":"Spyros Matsoukas","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Spyros Matsoukas","raw_affiliation_strings":["Alexa, Amazon.com Inc, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Alexa, Amazon.com Inc, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069416097","display_name":"Shiv Vitaladevuni","orcid":"https://orcid.org/0000-0003-2709-5145"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiv Vitaladevuni","raw_affiliation_strings":["Alexa, Amazon.com Inc, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Alexa, Amazon.com Inc, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101781558"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":2.7184,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.92023762,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7479","last_page":"7483"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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":0.9993000030517578,"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":0.8260576725006104},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.8128622770309448},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7174428105354309},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.6699154376983643},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6400489807128906},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5842208862304688},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5479292273521423},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4487805962562561},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41127943992614746}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8260576725006104},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.8128622770309448},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7174428105354309},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.6699154376983643},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6400489807128906},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5842208862304688},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5479292273521423},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4487805962562561},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41127943992614746},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053313","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053313","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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":34,"referenced_works":["https://openalex.org/W1990005915","https://openalex.org/W2001496424","https://openalex.org/W2034940213","https://openalex.org/W2058641082","https://openalex.org/W2062164080","https://openalex.org/W2117678320","https://openalex.org/W2405578611","https://openalex.org/W2406395231","https://openalex.org/W2407023693","https://openalex.org/W2407080277","https://openalex.org/W2507319753","https://openalex.org/W2507580616","https://openalex.org/W2696967604","https://openalex.org/W2748659049","https://openalex.org/W2748934350","https://openalex.org/W2787752687","https://openalex.org/W2797583228","https://openalex.org/W2797759721","https://openalex.org/W2887528618","https://openalex.org/W2891722048","https://openalex.org/W2905970125","https://openalex.org/W2936774411","https://openalex.org/W2962707338","https://openalex.org/W2963414149","https://openalex.org/W2963523217","https://openalex.org/W6713762819","https://openalex.org/W6713835734","https://openalex.org/W6713954808","https://openalex.org/W6714171909","https://openalex.org/W6739992741","https://openalex.org/W6748315512","https://openalex.org/W6750665317","https://openalex.org/W6753500843","https://openalex.org/W6757015787"],"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/W1989658893","https://openalex.org/W2545741539"],"abstract_inverted_index":{"Wake":[0],"word":[1],"(WW)":[2],"spotting":[3],"is":[4,76],"challenging":[5],"in":[6,14,21,44,62,142],"far-field":[7],"not":[8],"only":[9,118],"because":[10],"of":[11,31,47,78,95,121,160,167,170,177],"the":[12,19,41,45,60,89,107,132,140,153,168,178],"interference":[13],"signal":[15],"transmission":[16],"but":[17],"also":[18],"complexity":[20,141],"acoustic":[22,97,143],"environment.":[23],"Traditional":[24],"WW":[25,63,108,123],"model":[26,42,90,163],"training":[27,81,133],"requires":[28],"large":[29],"amount":[30,169],"in-domain":[32],"WW-specific":[33,171],"data":[34,85,150,172],"with":[35,83,100],"substantial":[36],"human":[37],"annotations.":[38],"This":[39],"prevents":[40],"building":[43],"situation":[46],"lacking":[48],"such":[49,65],"data.":[50],"In":[51],"this":[52],"paper":[53],"we":[54,125],"present":[55],"data-efficient":[56],"solutions":[57,155],"to":[58,92,105,128,138,173],"address":[59],"challenges":[61],"modeling,":[64],"as":[66],"domain-mismatch,":[67],"noisy":[68],"conditions,":[69,98],"limited":[70],"annotation,":[71],"etc.":[72],"Our":[73,145],"proposed":[74,154],"system":[75],"composed":[77],"a":[79,93,101,161],"multi-condition":[80],"pipeline":[82,104],"stratified":[84],"augmentation,":[86],"which":[87],"improves":[88],"robustness":[91],"variety":[94],"predefined":[96],"together":[99],"semi-supervised":[102],"learning":[103],"extract":[106],"and":[109,130,175],"adversarial":[110],"examples":[111],"from":[112,117],"untranscribed":[113],"speech":[114],"corpus.":[115],"Starting":[116],"10":[119],"hours":[120],"domain-mismatched":[122],"audio,":[124],"are":[126],"able":[127],"enlarge":[129],"enrich":[131],"dataset":[134],"by":[135,164],"20-100":[136],"times":[137],"capture":[139],"environments.":[144],"experiments":[146],"on":[147],"real":[148],"user":[149],"show":[151],"that":[152],"can":[156],"achieve":[157],"comparable":[158],"performance":[159],"production-grade":[162],"saving":[165],"97%":[166],"collect":[174],"86%":[176],"bandwidth":[179],"for":[180],"annotation.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-14T06:02:45.956762","created_date":"2025-10-10T00:00:00"}