{"id":"https://openalex.org/W3095735913","doi":"https://doi.org/10.21437/interspeech.2020-1992","title":"On Front-End Gain Invariant Modeling for Wake Word Spotting","display_name":"On Front-End Gain Invariant Modeling for Wake Word Spotting","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3095735913","doi":"https://doi.org/10.21437/interspeech.2020-1992","mag":"3095735913"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1992","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"conference-paper","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yixin Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110927557","display_name":"Noah D. Stein","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Noah D. Stein","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020775828","display_name":"Chieh-Chi Kao","orcid":"https://orcid.org/0000-0002-1161-3959"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chieh-Chi Kao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073824669","display_name":"Yunliang Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunliang Cai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100755311","display_name":"Ming Sun","orcid":"https://orcid.org/0000-0002-5948-2708"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375896","display_name":"Tao Zhang","orcid":"https://orcid.org/0000-0003-1817-8379"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5069416097","display_name":"Shiv Vitaladevuni","orcid":"https://orcid.org/0000-0003-2709-5145"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiv Naga Prasad Vitaladevuni","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8075,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.8724559,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"991","last_page":"995"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998000264167786,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/spotting","display_name":"Spotting","score":0.8465704917907715},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6731666922569275},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5285286903381348},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48243793845176697},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.47821399569511414},{"id":"https://openalex.org/keywords/constant-false-alarm-rate","display_name":"Constant false alarm rate","score":0.4622684717178345},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.4268348217010498},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41198021173477173},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3462282419204712}],"concepts":[{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.8465704917907715},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6731666922569275},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5285286903381348},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48243793845176697},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.47821399569511414},{"id":"https://openalex.org/C77052588","wikidata":"https://www.wikidata.org/wiki/Q644307","display_name":"Constant false alarm rate","level":2,"score":0.4622684717178345},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.4268348217010498},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41198021173477173},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3462282419204712},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1992","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W3119978414","https://openalex.org/W4286904253","https://openalex.org/W2516975559","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2117995638"],"abstract_inverted_index":{"Wake":[0],"word":[1],"(WW)":[2],"spotting":[3],"is":[4,57,66,85,91,159],"challenging":[5],"in":[6,14,21,182,188],"far-field":[7],"due":[8],"to":[9,45,68,79,93,106,113,129,161,171,179],"the":[10,18,46,54,60,82,89,94,115,120,125,131,135,154,157,173,193],"complexities":[11],"and":[12,17,29,39,152],"variations":[13,118],"acoustic":[15],"conditions":[16],"environmental":[19],"interference":[20],"signal":[22],"transmission.":[23],"A":[24],"suite":[25],"of":[26],"carefully":[27],"designed":[28],"optimized":[30],"audio":[31,43,62],"front-end":[32],"(AFE)":[33],"algorithms":[34],"help":[35],"mitigate":[36],"these":[37,99],"challenges":[38],"provide":[40],"better":[41],"quality":[42],"signals":[44],"downstream":[47],"modules":[48],"such":[49,71],"as":[50,72],"WW":[51,55,83,95,121,143],"spotter.":[52],"Since":[53],"model":[56,176,194],"trained":[58],"with":[59,134,156,195],"AFE-processed":[61],"data,":[63],"its":[64],"performance":[65,84,199],"sensitive":[67],"AFE":[69,90,116,162,167],"variations,":[70],"gain":[73,117,163,168],"changes.":[74,164],"In":[75],"addition,":[76],"when":[77,166],"deploying":[78],"new":[80,109],"devices,":[81],"not":[86],"guaranteed":[87],"because":[88],"unknown":[92],"model.":[96,122],"To":[97],"address":[98],"issues,":[100],"we":[101],"propose":[102],"a":[103,108],"novel":[104],"approach":[105],"use":[107],"feature":[110,136],"called":[111],"$\\Delta$LFBE":[112,158,196],"decouple":[114],"from":[119,148],"We":[123,140],"modified":[124],"neural":[126],"network":[127],"architectures":[128],"accommodate":[130],"delta":[132],"computation,":[133],"extraction":[137],"module":[138],"unchanged.":[139],"evaluate":[141],"our":[142],"models":[144,155],"using":[145],"data":[146],"collected":[147],"real":[149],"household":[150],"settings":[151],"showed":[153],"robust":[160],"Specifically,":[165],"changes":[169],"up":[170,178],"$\\pm$12dB,":[172],"baseline":[174],"CNN":[175],"lost":[177],"relative":[180],"19.0%":[181],"false":[183,189],"alarm":[184],"rate":[185],"or":[186],"34.3%":[187],"reject":[190],"rate,":[191],"while":[192],"demonstrates":[197],"no":[198],"loss.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}