{"id":"https://openalex.org/W2787752687","doi":"https://doi.org/10.1109/asru.2017.8268943","title":"Direct modeling of raw audio with DNNS for wake word detection","display_name":"Direct modeling of raw audio with DNNS for wake word detection","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2787752687","doi":"https://doi.org/10.1109/asru.2017.8268943","mag":"2787752687"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2017.8268943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268943","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5053915317","display_name":"Kenichi Kumatani","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kenichi Kumatani","raw_affiliation_strings":["Amazon Inc"],"affiliations":[{"raw_affiliation_string":"Amazon Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062398886","display_name":"Sankaran Panchapagesan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sankaran Panchapagesan","raw_affiliation_strings":["Amazon Inc"],"affiliations":[{"raw_affiliation_string":"Amazon Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060740546","display_name":"Minhua Wu","orcid":"https://orcid.org/0000-0001-9798-2984"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minhua Wu","raw_affiliation_strings":["Amazon Inc"],"affiliations":[{"raw_affiliation_string":"Amazon Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100340248","display_name":"Minjae Kim","orcid":"https://orcid.org/0000-0001-8746-1915"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minjae Kim","raw_affiliation_strings":["Amazon Inc"],"affiliations":[{"raw_affiliation_string":"Amazon Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028062647","display_name":"Nikko Str\u00f6m","orcid":"https://orcid.org/0000-0002-9295-7859"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikko Strom","raw_affiliation_strings":["Amazon Inc"],"affiliations":[{"raw_affiliation_string":"Amazon Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003334789","display_name":"Gautam Tiwari","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gautam Tiwari","raw_affiliation_strings":["Amazon Inc"],"affiliations":[{"raw_affiliation_string":"Amazon Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031791773","display_name":"Arindam Mandai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arindam Mandai","raw_affiliation_strings":["Amazon Inc"],"affiliations":[{"raw_affiliation_string":"Amazon Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5053915317"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.2874,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.97364245,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"252","last_page":"257"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9987000226974487,"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":0.7516876459121704},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6523865461349487},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5971807837486267},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5840489864349365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5239431858062744},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4918520450592041},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4771246910095215},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46686697006225586}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7516876459121704},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6523865461349487},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5971807837486267},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5840489864349365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5239431858062744},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4918520450592041},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4771246910095215},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46686697006225586},{"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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2017.8268943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268943","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1982728343","https://openalex.org/W2022011789","https://openalex.org/W2048060899","https://openalex.org/W2293968535","https://openalex.org/W2398826216","https://openalex.org/W2400092632","https://openalex.org/W2405578611","https://openalex.org/W2506203739","https://openalex.org/W2507319753","https://openalex.org/W2508048623","https://openalex.org/W2512499206","https://openalex.org/W2516857479","https://openalex.org/W2587529061","https://openalex.org/W2748659049","https://openalex.org/W2784023976","https://openalex.org/W3098773154","https://openalex.org/W4206633762","https://openalex.org/W6712560600","https://openalex.org/W6712742799","https://openalex.org/W6713835734"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W1987128138","https://openalex.org/W3013299381"],"abstract_inverted_index":{"In":[0,62],"this":[1,95,149],"work,":[2],"we":[3,64,107],"develop":[4],"a":[5,31,47,54,77,83,88,154,177,187],"technique":[6,152],"for":[7,52,176],"training":[8,53,151,191],"features":[9],"directly":[10,65],"from":[11,71],"the":[12,67,72,100,115,126,132,146,168,184,202,205],"single-channel":[13,73],"speech":[14,26],"waveform":[15],"in":[16,76,201],"order":[17],"to":[18,109],"improve":[19],"wake":[20],"word":[21],"(WW)":[22],"detection":[23],"performance.":[24],"Conventional":[25],"recognition":[27],"systems":[28],"typically":[29],"extract":[30],"compact":[32],"feature":[33,48,84,97,127,133],"representation":[34,98],"based":[35],"on":[36,158],"prior":[37],"knowledge":[38],"such":[39],"as":[40,106],"log-mel":[41],"filter":[42],"bank":[43],"energy":[44],"(LFBE).":[45],"Such":[46],"is":[49,119,193],"then":[50,141],"used":[51],"deep":[55],"neural":[56],"network":[57],"(DNN)":[58],"acoustic":[59],"model":[60],"(AM).":[61],"contrast,":[63],"train":[66,94,110],"WW":[68,112,116],"DNN":[69,86,118,170],"AM":[70],"audio":[74],"data":[75,192],"stage-wise":[78,150],"manner.":[79],"We":[80,144],"first":[81],"build":[82],"extraction":[85,128,134],"with":[87,121],"small":[89],"hidden":[90],"bottleneck":[91,96,123],"layer,":[92],"and":[93,135,140],"using":[99],"same":[101],"multi-task":[102],"cross-entropy":[103],"objective":[104],"function":[105],"use":[108],"our":[111],"DNNs.":[113],"Then,":[114],"classification":[117,136],"trained":[120],"input":[122],"features,":[124],"keeping":[125],"layers":[129],"fixed.":[130],"Finally,":[131],"DNNs":[137],"are":[138],"combined":[139],"jointly":[142],"optimized.":[143],"show":[145,166],"effectiveness":[147],"of":[148,156,179,190],"through":[153],"set":[155],"experiments":[157],"real":[159],"beam-formed":[160],"far-field":[161],"data.":[162],"The":[163],"experiment":[164],"results":[165],"that":[167],"audioinput":[169],"provides":[171],"significantly":[172],"lower":[173],"miss":[174],"rates":[175,182],"range":[178],"false":[180],"alarm":[181],"over":[183],"LFBE":[185],"when":[186],"sufficient":[188],"amount":[189],"available,":[194],"yielding":[195],"approximately":[196],"12":[197],"%":[198],"relative":[199],"improvement":[200],"area":[203],"under":[204],"curve":[206],"(AUC).":[207]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}