{"id":"https://openalex.org/W3047815947","doi":"https://doi.org/10.21437/interspeech.2020-1491","title":"Accurate Detection of Wake Word Start and End Using a CNN","display_name":"Accurate Detection of Wake Word Start and End Using a CNN","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3047815947","doi":"https://doi.org/10.21437/interspeech.2020-1491","mag":"3047815947"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1491","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1491","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2008.03790","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042851905","display_name":"Christin Jose","orcid":"https://orcid.org/0000-0002-7594-4490"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Christin Jose","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"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/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yuriy Mishchenko","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058266572","display_name":"Thibaud S\u00e9n\u00e9chal","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thibaud S\u00e9n\u00e9chal","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071440743","display_name":"Anish Shah","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Anish Shah","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068300265","display_name":"Alex Escott","orcid":"https://orcid.org/0000-0002-2683-624X"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alex Escott","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"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/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Shiv Naga Prasad Vitaladevuni","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5042851905"],"corresponding_institution_ids":["https://openalex.org/I4210089985"],"apc_list":null,"apc_paid":null,"fwci":0.1371,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55319056,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"3346","last_page":"3350"},"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":0.9993000030517578,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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":0.753324031829834},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7448055744171143},{"id":"https://openalex.org/keywords/wake","display_name":"Wake","score":0.6890890598297119},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6653774380683899},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5305426716804504},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.529778003692627},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4779115617275238},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.431709349155426},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07756549119949341},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06960254907608032},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06606414914131165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.753324031829834},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7448055744171143},{"id":"https://openalex.org/C48939323","wikidata":"https://www.wikidata.org/wiki/Q294879","display_name":"Wake","level":2,"score":0.6890890598297119},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6653774380683899},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5305426716804504},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.529778003692627},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4779115617275238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.431709349155426},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07756549119949341},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06960254907608032},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06606414914131165},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-1491","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1491","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"},{"id":"pmh:oai:arXiv.org:2008.03790","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.03790","pdf_url":"https://arxiv.org/pdf/2008.03790","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3047815947","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2008.03790.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2008.03790","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2008.03790","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2008.03790","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.03790","pdf_url":"https://arxiv.org/pdf/2008.03790","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2034940213","https://openalex.org/W2109207304","https://openalex.org/W2407023693","https://openalex.org/W2507319753","https://openalex.org/W2748659049","https://openalex.org/W2784023976","https://openalex.org/W2787752687","https://openalex.org/W2797759721","https://openalex.org/W2891722048"],"related_works":["https://openalex.org/W3096662840","https://openalex.org/W3089633658","https://openalex.org/W2846437026","https://openalex.org/W3136804610","https://openalex.org/W3025561721","https://openalex.org/W3181776258","https://openalex.org/W2902572630","https://openalex.org/W2963414149","https://openalex.org/W3133600743","https://openalex.org/W2898711434","https://openalex.org/W3155125158","https://openalex.org/W3176940907","https://openalex.org/W2397152345","https://openalex.org/W2011865252","https://openalex.org/W2110406951","https://openalex.org/W2963970535","https://openalex.org/W2746785844","https://openalex.org/W2827311432","https://openalex.org/W3097246512","https://openalex.org/W1992673181"],"abstract_inverted_index":{"Small":[0],"footprint":[1],"embedded":[2],"devices":[3],"require":[4],"keyword":[5,21],"spotters":[6],"(KWS)":[7],"with":[8,41,111],"small":[9],"model":[10],"size":[11],"and":[12,52],"detection":[13,132],"latency":[14],"for":[15,68,94,134],"enabling":[16],"voice":[17,36],"assistants.":[18],"Such":[19],"a":[20],"is":[22,31,54,124],"often":[23],"referred":[24],"to":[25,33,101],"as":[26,29],"\\textit{wake":[27],"word}":[28],"it":[30],"used":[32],"wake":[34,42,48,73,96,129],"up":[35,100],"assistant":[37],"enabled":[38],"devices.":[39],"Together":[40],"word":[43,49,130],"detection,":[44],"accurate":[45],"estimation":[46],"of":[47,58,72,99,128],"endpoints":[50,71,98,131],"(start":[51],"end)":[53],"an":[55],"important":[56],"task":[57],"KWS.":[59,137],"In":[60],"this":[61,123],"paper,":[62],"we":[63],"propose":[64],"two":[65],"new":[66,89],"methods":[67,133],"detecting":[69,95],"the":[70,88,112,125],"words":[74],"in":[75],"neural":[76,82,136],"KWS":[77],"that":[78,87],"use":[79],"single-stage":[80,135],"word-level":[81],"networks.":[83],"Our":[84],"results":[85],"show":[86],"techniques":[90],"give":[91],"superior":[92],"accuracy":[93],"words'":[97],"50":[102],"msec":[103],"standard":[104],"error":[105],"versus":[106],"human":[107],"annotations,":[108],"on":[109],"par":[110],"conventional":[113],"Acoustic":[114],"Model":[115],"plus":[116],"HMM":[117],"forced":[118],"alignment.":[119],"To":[120],"our":[121],"knowledge,":[122],"first":[126],"study":[127]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}