{"id":"https://openalex.org/W4375869136","doi":"https://doi.org/10.1109/icassp49357.2023.10095459","title":"The DKU Post-Challenge Audio-Visual Wake Word Spotting System for the 2021 MISP Challenge: Deep Analysis","display_name":"The DKU Post-Challenge Audio-Visual Wake Word Spotting System for the 2021 MISP Challenge: Deep Analysis","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869136","doi":"https://doi.org/10.1109/icassp49357.2023.10095459"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095459","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5016797242","display_name":"Haoxu Wang","orcid":"https://orcid.org/0000-0002-5430-0899"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]},{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoxu Wang","raw_affiliation_strings":["Wuhan University,School of Computer Science,Wuhan,China","Data Science Research Center, Duke Kunshan University, Kunshan, China","School of Computer Science, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Computer Science,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Data Science Research Center, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]},{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101639327","display_name":"Ming Cheng","orcid":"https://orcid.org/0000-0003-1819-650X"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Cheng","raw_affiliation_strings":["Wuhan University,School of Computer Science,Wuhan,China","School of Computer Science, Wuhan University, Wuhan, China","Data Science Research Center, Duke Kunshan University, Kunshan, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Computer Science,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Data Science Research Center, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002623953","display_name":"Qiang Fu","orcid":"https://orcid.org/0000-0001-6395-8521"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Fu","raw_affiliation_strings":["Alibaba Group,China","Alibaba Group, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092339704","display_name":"Ming Li","orcid":"https://orcid.org/0009-0006-1940-8024"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["Wuhan University,School of Computer Science,Wuhan,China","Data Science Research Center, Duke Kunshan University, Kunshan, China","School of Computer Science, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Computer Science,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Data Science Research Center, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]},{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5016797242"],"corresponding_institution_ids":["https://openalex.org/I37461747","https://openalex.org/I4210159968"],"apc_list":null,"apc_paid":null,"fwci":2.0332,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.87338048,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9997000098228455,"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/spotting","display_name":"Spotting","score":0.9349081516265869},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7811706066131592},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5505754947662354},{"id":"https://openalex.org/keywords/constant-false-alarm-rate","display_name":"Constant false alarm rate","score":0.5366783738136292},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.527677595615387},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4858645796775818},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.44522565603256226},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4368237853050232},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4330655038356781},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38677045702934265},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3304019868373871},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.25458428263664246}],"concepts":[{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.9349081516265869},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7811706066131592},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5505754947662354},{"id":"https://openalex.org/C77052588","wikidata":"https://www.wikidata.org/wiki/Q644307","display_name":"Constant false alarm rate","level":2,"score":0.5366783738136292},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.527677595615387},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4858645796775818},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.44522565603256226},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4368237853050232},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4330655038356781},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38677045702934265},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3304019868373871},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25458428263664246},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/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/icassp49357.2023.10095459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095459","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336618","display_name":"Science and Technology Program of Suzhou","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2079636521","https://openalex.org/W2168729028","https://openalex.org/W2407023693","https://openalex.org/W2748659049","https://openalex.org/W2752782242","https://openalex.org/W2884585870","https://openalex.org/W2890952074","https://openalex.org/W2897492880","https://openalex.org/W2936774411","https://openalex.org/W2943235166","https://openalex.org/W2963155035","https://openalex.org/W2969985801","https://openalex.org/W2973226577","https://openalex.org/W3006974783","https://openalex.org/W3019293601","https://openalex.org/W3082089446","https://openalex.org/W3094791070","https://openalex.org/W3097777922","https://openalex.org/W3162293946","https://openalex.org/W3163237592","https://openalex.org/W3166716987","https://openalex.org/W3206287456","https://openalex.org/W4224213421","https://openalex.org/W4224933780","https://openalex.org/W4224940398","https://openalex.org/W4297841411","https://openalex.org/W4297841644","https://openalex.org/W4312636357","https://openalex.org/W6753412334","https://openalex.org/W6754392867","https://openalex.org/W6761937618","https://openalex.org/W6782374147","https://openalex.org/W6796538260","https://openalex.org/W6848260148"],"related_works":["https://openalex.org/W2742860341","https://openalex.org/W4248007934","https://openalex.org/W3018114492","https://openalex.org/W1483316057","https://openalex.org/W1554833030","https://openalex.org/W2323788589","https://openalex.org/W2058491579","https://openalex.org/W2752634058","https://openalex.org/W208599549","https://openalex.org/W2171506966"],"abstract_inverted_index":{"This":[0],"paper":[1],"further":[2],"explores":[3],"our":[4,41],"previous":[5,131],"wake":[6],"word":[7],"spotting":[8],"system":[9,42,73,96],"ranked":[10],"2-nd":[11],"in":[12,91,111],"Track":[13],"1":[14],"of":[15,51,88,102,109,115],"the":[16,35,61,79,85,112,116,121],"MISP":[17],"Challenge":[18],"2021.":[19],"First,":[20],"we":[21,47,59],"investigate":[22],"a":[23,98,105],"robust":[24],"unimodal":[25],"approach":[26],"based":[27],"on":[28],"3D":[29],"and":[30,33,67,77,104],"2D":[31],"convolution":[32],"adopt":[34],"simple":[36],"attention":[37],"module":[38],"(SimAM)":[39],"for":[40,55],"to":[43,83,130],"improve":[44],"performance.":[45,57],"Second,":[46],"explore":[48],"different":[49],"combinations":[50],"data":[52],"augmentation":[53],"methods":[54],"better":[56],"Finally,":[58],"study":[60],"fusion":[62],"strategies,":[63],"including":[64],"score-level,":[65],"cascaded":[66],"neural":[68],"fusion.":[69],"Our":[70,95],"proposed":[71],"multimodal":[72,75],"leverages":[74],"features":[76],"uses":[78],"complementary":[80],"visual":[81],"information":[82],"mitigate":[84],"performance":[86,124],"degradation":[87],"audio-only":[89],"systems":[90],"complex":[92],"acoustic":[93],"scenarios.":[94],"obtains":[97],"false":[99,106],"reject":[100],"rate":[101,108],"2.15%":[103],"alarm":[107],"3.44%":[110],"evaluation":[113],"set":[114],"competition":[117],"database,":[118],"which":[119],"achieves":[120],"new":[122],"state-of-the-art":[123],"by":[125],"21%":[126],"relative":[127],"improvement":[128],"compared":[129],"systems.":[132],"Related":[133],"resource":[134],"can":[135],"be":[136],"found":[137],"at:":[138],"https://github.com/Mashiro009/DKU_WWS_MISP.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":9}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
