{"id":"https://openalex.org/W4284966478","doi":"https://doi.org/10.21437/interspeech.2022-529","title":"Low-resource Low-footprint Wake-word Detection using Knowledge Distillation","display_name":"Low-resource Low-footprint Wake-word Detection using Knowledge Distillation","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4284966478","doi":"https://doi.org/10.21437/interspeech.2022-529"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-529","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-529","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5102007466","display_name":"Arindam Ghosh","orcid":"https://orcid.org/0000-0003-2426-3115"},"institutions":[{"id":"https://openalex.org/I4210123366","display_name":"Health Information Management","ror":"https://ror.org/02zmq8s40","country_code":"BE","type":"other","lineage":["https://openalex.org/I4210123366"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Arindam Ghosh","raw_affiliation_strings":["3M Health Information Systems"],"affiliations":[{"raw_affiliation_string":"3M Health Information Systems","institution_ids":["https://openalex.org/I4210123366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005148508","display_name":"Mark C. Fuhs","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123366","display_name":"Health Information Management","ror":"https://ror.org/02zmq8s40","country_code":"BE","type":"other","lineage":["https://openalex.org/I4210123366"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Mark Fuhs","raw_affiliation_strings":["3M Health Information Systems"],"affiliations":[{"raw_affiliation_string":"3M Health Information Systems","institution_ids":["https://openalex.org/I4210123366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089667871","display_name":"Deblin Bagchi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123366","display_name":"Health Information Management","ror":"https://ror.org/02zmq8s40","country_code":"BE","type":"other","lineage":["https://openalex.org/I4210123366"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Deblin Bagchi","raw_affiliation_strings":["3M Health Information Systems"],"affiliations":[{"raw_affiliation_string":"3M Health Information Systems","institution_ids":["https://openalex.org/I4210123366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034867725","display_name":"Bahman Farahani","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123366","display_name":"Health Information Management","ror":"https://ror.org/02zmq8s40","country_code":"BE","type":"other","lineage":["https://openalex.org/I4210123366"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Bahman Farahani","raw_affiliation_strings":["3M Health Information Systems"],"affiliations":[{"raw_affiliation_string":"3M Health Information Systems","institution_ids":["https://openalex.org/I4210123366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053580599","display_name":"Monika Woszczyna","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123366","display_name":"Health Information Management","ror":"https://ror.org/02zmq8s40","country_code":"BE","type":"other","lineage":["https://openalex.org/I4210123366"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Monika Woszczyna","raw_affiliation_strings":["3M Health Information Systems"],"affiliations":[{"raw_affiliation_string":"3M Health Information Systems","institution_ids":["https://openalex.org/I4210123366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102007466"],"corresponding_institution_ids":["https://openalex.org/I4210123366"],"apc_list":null,"apc_paid":null,"fwci":0.5194,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.62055591,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3739","last_page":"3743"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9976000189781189,"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":0.9975000023841858,"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/footprint","display_name":"Footprint","score":0.8005247116088867},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6179441213607788},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5732470750808716},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.525924801826477},{"id":"https://openalex.org/keywords/wake","display_name":"Wake","score":0.5192618370056152},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4761807322502136},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32389116287231445},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15290239453315735},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09343650937080383},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.0873681902885437}],"concepts":[{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.8005247116088867},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6179441213607788},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5732470750808716},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.525924801826477},{"id":"https://openalex.org/C48939323","wikidata":"https://www.wikidata.org/wiki/Q294879","display_name":"Wake","level":2,"score":0.5192618370056152},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4761807322502136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32389116287231445},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15290239453315735},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09343650937080383},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0873681902885437},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-529","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-529","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1821462560","https://openalex.org/W2034940213","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2407080277","https://openalex.org/W2507580616","https://openalex.org/W2514741789","https://openalex.org/W2696967604","https://openalex.org/W2748659049","https://openalex.org/W2888867175","https://openalex.org/W2889282842","https://openalex.org/W2892008152","https://openalex.org/W2913178639","https://openalex.org/W2937308178","https://openalex.org/W2963628261","https://openalex.org/W2963864497","https://openalex.org/W3012505451","https://openalex.org/W3041133507","https://openalex.org/W3094791070","https://openalex.org/W3161145038","https://openalex.org/W3197949759"],"related_works":["https://openalex.org/W2757285599","https://openalex.org/W2376025146","https://openalex.org/W161151693","https://openalex.org/W3195741387","https://openalex.org/W2314669870","https://openalex.org/W2883444180","https://openalex.org/W4381570180","https://openalex.org/W2955635855","https://openalex.org/W4324257240","https://openalex.org/W2379898265"],"abstract_inverted_index":{"As":[0],"virtual":[1],"assistants":[2],"have":[3],"become":[4],"more":[5,82],"diverse":[6],"and":[7,55,80,89],"specialized,":[8],"so":[9],"has":[10],"the":[11,19,75],"demand":[12],"for":[13,43,106],"application":[14],"or":[15],"brand-specific":[16],"wake":[17],"words.However,":[18],"wake-word-specific":[20],"datasets":[21,108],"typically":[22],"used":[23],"to":[24,30,38,47,68,100],"train":[25],"wake-word":[26,51],"detectors":[27],"are":[28,72,98],"costly":[29],"create.In":[31],"this":[32],"paper,":[33],"we":[34,97],"explore":[35,59],"two":[36],"techniques":[37,62],"leverage":[39],"acoustic":[40,95],"modeling":[41],"data":[42],"large-vocabulary":[44],"speech":[45],"recognition":[46],"improve":[48,69,101],"a":[49,81,93],"purpose-built":[50],"detector:":[52],"transfer":[53],"learning":[54],"knowledge":[56,90],"distillation.We":[57],"also":[58],"how":[60],"these":[61],"interact":[63],"with":[64],"timesynchronous":[65],"training":[66],"targets":[67,88],"detection":[70],"latency.Experiments":[71],"presented":[73],"on":[74],"open-source":[76],"\"Hey":[77],"Snips\"":[78],"dataset":[79,104],"challenging":[83],"in-house":[84],"far-field":[85],"dataset.Using":[86],"phonesynchronous":[87],"distillation":[91],"from":[92],"large":[94],"model,":[96],"able":[99],"accuracy":[102],"across":[103],"sizes":[105],"both":[107],"while":[109],"reducing":[110],"latency.":[111]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}