{"id":"https://openalex.org/W3089633658","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207489","title":"Two-stage Strategy for Small-footprint Wake-up-word Speech Recognition System","display_name":"Two-stage Strategy for Small-footprint Wake-up-word Speech Recognition System","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3089633658","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207489","mag":"3089633658"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9207489","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207489","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","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/A5052564067","display_name":"Xinya You","orcid":"https://orcid.org/0000-0002-0220-8572"},"institutions":[{"id":"https://openalex.org/I55022517","display_name":"Heilongjiang University","ror":"https://ror.org/04zyhq975","country_code":"CN","type":"education","lineage":["https://openalex.org/I55022517"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinya You","raw_affiliation_strings":["Heilongjiang University"],"affiliations":[{"raw_affiliation_string":"Heilongjiang University","institution_ids":["https://openalex.org/I55022517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101433524","display_name":"Yajie Zhao","orcid":"https://orcid.org/0000-0002-3717-9513"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yajie Zhao","raw_affiliation_strings":["Columbia University in the City of New York"],"affiliations":[{"raw_affiliation_string":"Columbia University in the City of New York","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076566232","display_name":"Mingyuan Sun","orcid":"https://orcid.org/0000-0002-6061-7198"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Mingyuan Sun","raw_affiliation_strings":["Northeastern University"],"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5052564067"],"corresponding_institution_ids":["https://openalex.org/I55022517"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11646443,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9986000061035156,"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":0.9965000152587891,"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":0.8153905868530273},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6953893899917603},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5527889132499695},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.510137140750885},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.45316022634506226},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44760626554489136},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44579434394836426},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4456419050693512},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4217243790626526},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3138720393180847},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.0992169976234436},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06888529658317566}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8153905868530273},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6953893899917603},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5527889132499695},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.510137140750885},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.45316022634506226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44760626554489136},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44579434394836426},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4456419050693512},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4217243790626526},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3138720393180847},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0992169976234436},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06888529658317566},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9207489","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207489","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1496120315","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1560013842","https://openalex.org/W2011865252","https://openalex.org/W2017921836","https://openalex.org/W2034940213","https://openalex.org/W2058641082","https://openalex.org/W2069737407","https://openalex.org/W2097207027","https://openalex.org/W2155273149","https://openalex.org/W2164890161","https://openalex.org/W2271840356","https://openalex.org/W2407023693","https://openalex.org/W2608183891","https://openalex.org/W2613303405","https://openalex.org/W2652238127","https://openalex.org/W2888845873","https://openalex.org/W2902572630","https://openalex.org/W2962961542","https://openalex.org/W2964121744","https://openalex.org/W3105118415","https://openalex.org/W6629574835","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6659477065","https://openalex.org/W6684337689","https://openalex.org/W6694517276","https://openalex.org/W6714171909","https://openalex.org/W6740275694","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340","https://openalex.org/W4229451372"],"abstract_inverted_index":{"In":[0,22,54,95],"this":[1,118],"paper,":[2],"we":[3,58],"propose":[4],"a":[5,18,41],"small-footprint":[6],"wake-":[7],"up-word":[8],"speech":[9,84],"recognition":[10],"(WUWSR)":[11],"system":[12,106],"with":[13],"two":[14],"stages":[15],"to":[16,32,46,74],"recognize":[17],"two-syllable":[19],"wake-up":[20,86],"word.":[21],"the":[23,34,47,55,76,89,93,98,104,115],"first":[24,79],"stage,":[25,57],"convolution":[26],"neural":[27],"network":[28,64,71],"(CNN)":[29],"is":[30,43],"trained":[31],"predict":[33],"posterior":[35],"probability":[36],"of":[37,100,117],"context-dependent":[38],"state.":[39],"Thus":[40],"wake-up-word":[42],"detected":[44],"according":[45],"confidence":[48],"score":[49],"obtained":[50],"by":[51],"dynamic":[52],"programming.":[53],"second":[56,90],"cascade":[59],"bidirectional":[60],"long":[61],"short-term":[62],"memory":[63],"(LSTM),":[65],"convolutional":[66],"modules":[67],"and":[68,88,127],"deep":[69],"feed-forward":[70],"(BLCDNN)":[72],"successively":[73],"verify":[75],"detection.":[77,94],"The":[78,111],"stage":[80,91],"quickly":[81],"filters":[82],"out":[83],"without":[85,97],"word,":[87],"refines":[92],"addition,":[96],"intervention":[99],"any":[101],"decoding":[102],"modules,":[103],"proposed":[105],"can":[107],"guarantee":[108],"low":[109,129],"latency.":[110],"experimental":[112],"results":[113],"demonstrate":[114],"effectiveness":[116],"method.":[119],"Our":[120],"system,":[121],"named":[122],"CNN-BLCDNN,":[123],"reaches":[124],"high":[125],"accuracy":[126],"maintains":[128],"false":[130],"alarm":[131],"rate.":[132]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}