{"id":"https://openalex.org/W2891722048","doi":"https://doi.org/10.1109/icassp.2018.8462166","title":"Time-Delayed Bottleneck Highway Networks Using a DFT Feature for Keyword Spotting","display_name":"Time-Delayed Bottleneck Highway Networks Using a DFT Feature for Keyword Spotting","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2891722048","doi":"https://doi.org/10.1109/icassp.2018.8462166","mag":"2891722048"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462166","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5103232491","display_name":"Jinxi Guo","orcid":"https://orcid.org/0000-0001-9563-7351"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinxi Guo","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California, Los Angeles, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053915317","display_name":"Kenichi Kumatani","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kenichi Kumatani","raw_affiliation_strings":["Amazon Inc, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Inc, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100755311","display_name":"Ming Sun","orcid":"https://orcid.org/0000-0002-5948-2708"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming Sun","raw_affiliation_strings":["Amazon Inc, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Inc, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060740546","display_name":"Minhua Wu","orcid":"https://orcid.org/0000-0001-9798-2984"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minhua Wu","raw_affiliation_strings":["Amazon Inc, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Inc, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109046112","display_name":"Anirudh Raju","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anirudh Raju","raw_affiliation_strings":["Amazon Inc, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Inc, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028062647","display_name":"Nikko Str\u00f6m","orcid":"https://orcid.org/0000-0002-9295-7859"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikko Strom","raw_affiliation_strings":["Amazon Inc, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Inc, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059342552","display_name":"Arindam Mandal","orcid":"https://orcid.org/0000-0003-2804-3638"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arindam Mandal","raw_affiliation_strings":["Amazon Inc, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Inc, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.9532,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.97345133,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5489","last_page":"5493"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9879000186920166,"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":0.9868999719619751,"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/bottleneck","display_name":"Bottleneck","score":0.8330667018890381},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7084743976593018},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.7000119686126709},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5885307788848877},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4907277822494507},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4825717508792877},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47708162665367126},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3510853052139282},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.09590765833854675}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8330667018890381},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7084743976593018},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.7000119686126709},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5885307788848877},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4907277822494507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4825717508792877},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47708162665367126},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3510853052139282},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.09590765833854675},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462166","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"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/W2507580616","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/W2787752687","https://openalex.org/W2797759721","https://openalex.org/W2963124866","https://openalex.org/W3098773154","https://openalex.org/W4206633762","https://openalex.org/W6655988562","https://openalex.org/W6696002848","https://openalex.org/W6712560600","https://openalex.org/W6712742799","https://openalex.org/W6713835734","https://openalex.org/W6747603249","https://openalex.org/W6748315512","https://openalex.org/W6750679367"],"related_works":["https://openalex.org/W2114097550","https://openalex.org/W2595172197","https://openalex.org/W4385352507","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2918559346","https://openalex.org/W84309476","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W105599799"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,15,36,59,101,106,116,141,168],"novel":[4],"deep":[5,212],"neural":[6],"network":[7,104,156],"(DNN)":[8],"architecture":[9],"with":[10,35,50,105,157],"highway":[11,213],"blocks":[12],"(HWs)":[13],"using":[14],"complex":[16,137,159],"discrete":[17],"Fourier":[18],"transform":[19],"(DFT)":[20],"feature":[21,56,118,139,161],"for":[22,167,198,210],"keyword":[23,199],"spotting.":[24,200],"In":[25,93],"our":[26],"previous":[27],"work,":[28],"we":[29,99,134,202],"showed":[30],"that":[31,153],"the":[32,44,48,51,67,89,97,124,136,149,154,158,175,185,188,192,204,211],"feed-forward":[33],"DNN":[34,75],"time-delayed":[37,107],"bottleneck":[38,108,117],"layer":[39,109],"(TDB-DNN)":[40],"directly":[41],"trained":[42],"from":[43],"audio":[45,73],"input":[46,74],"outperformed":[47],"model":[49],"log-mel":[52],"filter":[53],"bank":[54],"energy":[55],"(LFBE),":[57],"given":[58],"large":[60],"amount":[61],"of":[62,70,88,143,170,191,206],"training":[63,129],"data":[64,151],"[1].":[65,132],"However,":[66],"deeper":[68],"structure":[69],"such":[71],"an":[72,77],"makes":[76],"optimization":[78,121],"problem":[79],"more":[80],"difficult,":[81],"which":[82],"could":[83],"easily":[84],"fall":[85],"in":[86,131,184],"one":[87],"local":[90],"minimum":[91],"solutions.":[92],"order":[94],"to":[95],"alleviate":[96],"problem,":[98],"propose":[100],"new":[102],"HW":[103],"(TDB-HW).":[110],"Our":[111,145],"TDB-HW":[112,155],"networks":[113],"can":[114],"learn":[115],"representation":[119],"through":[120],"based":[122],"on":[123,148],"cross-entropy":[125],"criterion":[126],"without":[127],"stage-wise":[128],"proposed":[130],"Moreover,":[133],"use":[135],"DFT":[138,160],"as":[140],"method":[142],"pre-processing.":[144],"experimental":[146],"results":[147],"real":[150],"show":[152],"provides":[162],"significantly":[163],"lower":[164],"miss":[165],"rates":[166,173],"range":[169],"false":[171],"alarm":[172],"over":[174],"LFBE":[176],"DNN,":[177],"yielding":[178],"approximately":[179],"20":[180],"%":[181],"relative":[182],"improvement":[183],"area":[186],"under":[187],"curve":[189],"(AUC)":[190],"detection":[193],"error":[194],"tradeoff":[195],"(DET)":[196],"curves":[197],"Furthermore,":[201],"investigate":[203],"effects":[205],"different":[207],"pre-processing":[208],"methods":[209],"network.":[214]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}