{"id":"https://openalex.org/W3007380371","doi":"https://doi.org/10.1109/bigdata47090.2019.9006601","title":"Eliminating Data Collection Bottleneck for Wake Word Engine Training Using Found and Synthetic Data","display_name":"Eliminating Data Collection Bottleneck for Wake Word Engine Training Using Found and Synthetic Data","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3007380371","doi":"https://doi.org/10.1109/bigdata47090.2019.9006601","mag":"3007380371"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata47090.2019.9006601","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9006601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big Data)","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/A5079851149","display_name":"Buvaneswari Ramanan","orcid":null},"institutions":[{"id":"https://openalex.org/I72090969","display_name":"Nokia (United States)","ror":"https://ror.org/038km2573","country_code":"US","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I72090969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Buvaneswari Ramanan","raw_affiliation_strings":["Nokia Bell Labs, Murray Hill, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Nokia Bell Labs, Murray Hill, NJ, USA","institution_ids":["https://openalex.org/I72090969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040352022","display_name":"Lawrence Drabeck","orcid":null},"institutions":[{"id":"https://openalex.org/I72090969","display_name":"Nokia (United States)","ror":"https://ror.org/038km2573","country_code":"US","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I72090969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lawrence Drabeck","raw_affiliation_strings":["Nokia Bell Labs, Murray Hill, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Nokia Bell Labs, Murray Hill, NJ, USA","institution_ids":["https://openalex.org/I72090969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069403056","display_name":"Thomas Woo","orcid":"https://orcid.org/0009-0003-2028-5533"},"institutions":[{"id":"https://openalex.org/I72090969","display_name":"Nokia (United States)","ror":"https://ror.org/038km2573","country_code":"US","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I72090969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Woo","raw_affiliation_strings":["Nokia Bell Labs, Murray Hill, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Nokia Bell Labs, Murray Hill, NJ, USA","institution_ids":["https://openalex.org/I72090969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060799266","display_name":"Troy Cauble","orcid":null},"institutions":[{"id":"https://openalex.org/I72090969","display_name":"Nokia (United States)","ror":"https://ror.org/038km2573","country_code":"US","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I72090969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Troy Cauble","raw_affiliation_strings":["Nokia Bell Labs, Murray Hill, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Nokia Bell Labs, Murray Hill, NJ, USA","institution_ids":["https://openalex.org/I72090969"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005614987","display_name":"Anil Rana","orcid":"https://orcid.org/0000-0001-7476-6234"},"institutions":[{"id":"https://openalex.org/I72090969","display_name":"Nokia (United States)","ror":"https://ror.org/038km2573","country_code":"US","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I72090969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anil Rana","raw_affiliation_strings":["Nokia Bell Labs, Murray Hill, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Nokia Bell Labs, Murray Hill, NJ, USA","institution_ids":["https://openalex.org/I72090969"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5079851149"],"corresponding_institution_ids":["https://openalex.org/I72090969"],"apc_list":null,"apc_paid":null,"fwci":0.4201,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.72743716,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2447","last_page":"2456"},"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/T10028","display_name":"Topic Modeling","score":0.9980000257492065,"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/T12031","display_name":"Speech and dialogue systems","score":0.996399998664856,"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/computer-science","display_name":"Computer science","score":0.7928061485290527},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6821642518043518},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5860937237739563},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.5481904745101929},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5416572093963623},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4854646325111389},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4794099032878876},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4262327551841736},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3256458044052124},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08916500210762024}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7928061485290527},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6821642518043518},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5860937237739563},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.5481904745101929},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5416572093963623},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4854646325111389},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4794099032878876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4262327551841736},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3256458044052124},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08916500210762024},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata47090.2019.9006601","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9006601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big Data)","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":58,"referenced_works":["https://openalex.org/W1999121090","https://openalex.org/W2034940213","https://openalex.org/W2101346879","https://openalex.org/W2120847449","https://openalex.org/W2122797512","https://openalex.org/W2251321385","https://openalex.org/W2431874326","https://openalex.org/W2519091744","https://openalex.org/W2587529061","https://openalex.org/W2601450892","https://openalex.org/W2604763608","https://openalex.org/W2612434969","https://openalex.org/W2619368999","https://openalex.org/W2726515241","https://openalex.org/W2752796333","https://openalex.org/W2780351918","https://openalex.org/W2794490148","https://openalex.org/W2808631503","https://openalex.org/W2808706139","https://openalex.org/W2889162046","https://openalex.org/W2891499495","https://openalex.org/W2892743843","https://openalex.org/W2898727538","https://openalex.org/W2904601236","https://openalex.org/W2905970125","https://openalex.org/W2910655080","https://openalex.org/W2912937645","https://openalex.org/W2916104401","https://openalex.org/W2952396896","https://openalex.org/W2953219395","https://openalex.org/W2962802801","https://openalex.org/W2962993399","https://openalex.org/W2963341924","https://openalex.org/W2963414149","https://openalex.org/W2963539064","https://openalex.org/W2963628261","https://openalex.org/W2963799213","https://openalex.org/W2963975282","https://openalex.org/W2964120993","https://openalex.org/W2964161387","https://openalex.org/W2964187693","https://openalex.org/W3091905774","https://openalex.org/W3098773154","https://openalex.org/W6691770337","https://openalex.org/W6717697761","https://openalex.org/W6735236233","https://openalex.org/W6737575990","https://openalex.org/W6750489868","https://openalex.org/W6752888775","https://openalex.org/W6753855596","https://openalex.org/W6754600854","https://openalex.org/W6754829988","https://openalex.org/W6754960363","https://openalex.org/W6756385397","https://openalex.org/W6757472134","https://openalex.org/W6765987481","https://openalex.org/W6766442783","https://openalex.org/W6783596713"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W4382618745","https://openalex.org/W2885125400","https://openalex.org/W1001352512","https://openalex.org/W1989889224","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W1987128138"],"abstract_inverted_index":{"Voice":[0,135],"interfaces":[1],"are":[2,14,23,146],"fast":[3],"becoming":[4],"an":[5,237],"important":[6],"human-machine":[7],"interfaces,":[8],"and":[9,67,110,118,134,182,213,220],"Wake":[10],"Word":[11],"Engines":[12],"(WWEs)":[13],"a":[15,60,153,185,201],"critical":[16],"part":[17],"of":[18,43,57,127,155,190,211,234,239],"modern":[19],"voice":[20],"interfaces.":[21],"There":[22],"recent":[24],"advancements":[25],"in":[26,175],"applying":[27],"Deep":[28,32],"Learning":[29],"(DL)":[30],"or":[31],"Neural":[33],"Network":[34],"architectures":[35],"for":[36,77,86,108,184,222],"WWE":[37,79,140],"construction.":[38],"Similar":[39],"to":[40,132,137,148,217],"other":[41],"applications":[42],"DL":[44],"however,":[45],"achieving":[46],"good":[47],"accuracy":[48],"strongly":[49],"depends":[50],"on":[51],"training":[52],"using":[53,178,226],"the":[54,84,125,161,218,223],"right":[55],"type":[56],"dataset":[58],"-":[59],"task":[61],"that":[62,81,151,157],"traditionally":[63],"requires":[64],"significant":[65],"time":[66,232],"human":[68,168,229],"effort.":[69],"In":[70],"this":[71],"paper,":[72],"we":[73,93,101,123,145],"present":[74],"novel":[75,198],"techniques":[76],"curating":[78],"datasets":[80],"significantly":[82],"minimizes":[83],"need":[85],"data":[87,105,112,165,227],"collection":[88,169],"from":[89,113,166,228],"humans.":[90],"More":[91],"specifically,":[92],"investigated":[94],"two":[95],"techniques:":[96],"(1)":[97],"Using":[98,120,142],"\u201cFound":[99],"Data\u201d:":[100],"have":[102],"created":[103],"automated":[104],"curation":[106],"pipelines":[107],"locating":[109],"processing":[111],"public":[114],"sources":[115],"(e.g.,":[116,170],"YouTube),":[117],"(2)":[119],"Synthetic":[121],"Data:":[122],"explored":[124],"use":[126],"Synthesized":[128],"Speech":[129,133],"(using":[130],"Text":[131],"Conversion)":[136],"synthetically":[138],"generate":[139],"datasets.":[141],"our":[143,176,197],"techniques,":[144],"able":[147],"train":[149],"WWEs":[150,162,194],"demonstrate":[152],"level":[154],"performance":[156],"is":[158,241],"on-par":[159],"with":[160,164,196],"trained":[163,195,225],"expensive":[167],"Mechanical":[171],"Turk).":[172],"For":[173],"example,":[174],"experiments":[177],"wake":[179],"words":[180],"`Computer'":[181],"`Shannon',":[183],"given":[186],"False":[187,202],"Alarm":[188],"rate":[189],"1":[191],"per":[192],"hour,":[193],"methods":[199],"exhibit":[200],"Reject":[203],"Rate,":[204],"averaged":[205],"across":[206],"four":[207],"different":[208],"test":[209],"environments,":[210],"0.9%":[212],"1.6%":[214],"respectively":[215],"compared":[216],"1.0%":[219],"0.8%":[221],"baseline":[224],"collection.":[230],"Cycle":[231],"savings":[233],"more":[235],"than":[236],"order":[238],"magnitude":[240],"possible":[242],"by":[243],"utilizing":[244],"these":[245],"methods.":[246]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}