{"id":"https://openalex.org/W4224940398","doi":"https://doi.org/10.1109/icassp43922.2022.9747216","title":"The DKU Audio-Visual Wake Word Spotting System for the 2021 MISP Challenge","display_name":"The DKU Audio-Visual Wake Word Spotting System for the 2021 MISP Challenge","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224940398","doi":"https://doi.org/10.1109/icassp43922.2022.9747216"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747216","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747216","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5043443688","display_name":"Ming Shien Cheng","orcid":"https://orcid.org/0000-0002-7311-2690"},"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":"Ming Cheng","raw_affiliation_strings":["School of Computer Science, Wuhan University,Wuhan,China","School of Computer Science, Wuhan University, Wuhan, China","Data Science Research Center, Duke Kunshan University, Kunshan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University,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/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":false,"raw_author_name":"Haoxu Wang","raw_affiliation_strings":["School of Computer Science, Wuhan University,Wuhan,China","School of Computer Science, Wuhan University, Wuhan, China","Data Science Research Center, Duke Kunshan University, Kunshan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University,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/A5075634171","display_name":"Yechen Wang","orcid":"https://orcid.org/0009-0006-9419-4206"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yechen Wang","raw_affiliation_strings":["Data Science Research Center, Duke Kunshan University,Kunshan,China","Data Science Research Center, Duke Kunshan University, Kunshan, China"],"affiliations":[{"raw_affiliation_string":"Data Science Research Center, Duke Kunshan University,Kunshan,China","institution_ids":["https://openalex.org/I4210159968"]},{"raw_affiliation_string":"Data Science Research Center, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100351449","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-6406-1983"},"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":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["School of Computer Science, Wuhan University,Wuhan,China","School of Computer Science, Wuhan University, Wuhan, China","Data Science Research Center, Duke Kunshan University, Kunshan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University,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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5043443688"],"corresponding_institution_ids":["https://openalex.org/I37461747","https://openalex.org/I4210159968"],"apc_list":null,"apc_paid":null,"fwci":1.7183,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.87014218,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"9256","last_page":"9260"},"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":0.998199999332428,"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":0.9470267295837402},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7765110731124878},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.547821044921875},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.5138766765594482},{"id":"https://openalex.org/keywords/constant-false-alarm-rate","display_name":"Constant false alarm rate","score":0.45914149284362793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4406457841396332},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43289482593536377},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41722768545150757}],"concepts":[{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.9470267295837402},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7765110731124878},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.547821044921875},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.5138766765594482},{"id":"https://openalex.org/C77052588","wikidata":"https://www.wikidata.org/wiki/Q644307","display_name":"Constant false alarm rate","level":2,"score":0.45914149284362793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4406457841396332},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43289482593536377},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41722768545150757},{"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/icassp43922.2022.9747216","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747216","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5099999904632568,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1553469512","https://openalex.org/W1999121090","https://openalex.org/W2074671152","https://openalex.org/W2101234009","https://openalex.org/W2101346879","https://openalex.org/W2122797512","https://openalex.org/W2142384583","https://openalex.org/W2168729028","https://openalex.org/W2194775991","https://openalex.org/W2407023693","https://openalex.org/W2889839708","https://openalex.org/W2897492880","https://openalex.org/W2943235166","https://openalex.org/W2963155035","https://openalex.org/W2963247196","https://openalex.org/W2963616706","https://openalex.org/W2963820951","https://openalex.org/W2969985801","https://openalex.org/W2973000846","https://openalex.org/W2973226577","https://openalex.org/W3015273269","https://openalex.org/W3094700205","https://openalex.org/W3097018422","https://openalex.org/W3163237592","https://openalex.org/W3208743843","https://openalex.org/W4224933780","https://openalex.org/W6675354045","https://openalex.org/W6744865055","https://openalex.org/W6755759972","https://openalex.org/W6761937618","https://openalex.org/W6802609832"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W3119978414","https://openalex.org/W2114097550","https://openalex.org/W2545741539","https://openalex.org/W2516975559","https://openalex.org/W3206647229","https://openalex.org/W4286904253","https://openalex.org/W2000885660","https://openalex.org/W1969408022","https://openalex.org/W1483316057"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,7,11,26,116,120,127,133],"system":[4,75,97],"developed":[5],"by":[6],"DKU":[8],"team":[9],"for":[10,25],"MISP":[12,134],"Challenge":[13],"2021.":[14],"We":[15,32],"present":[16],"a":[17,42,59,77,99,106],"two-stage":[18],"approach":[19],"consisting":[20,82],"of":[21,83,103,110,119,132],"end-to-end":[22,84],"neural":[23,85],"networks":[24],"audio-visual":[27,68],"wake":[28,128],"word":[29,129],"spotting":[30,130],"task.":[31],"first":[33],"process":[34],"audio":[35,114],"and":[36,45,79,90,105],"video":[37],"data":[38,92],"to":[39],"give":[40],"them":[41],"similar":[43],"structure":[44],"then":[46],"train":[47],"two":[48],"unimodal":[49,72],"models":[50],"with":[51],"unified":[52],"network":[53],"architecture":[54],"separately.":[55],"Second,":[56],"we":[57],"propose":[58],"Hierarchical":[60],"Modality":[61],"Aggregation":[62],"(HMA)":[63],"module":[64],"that":[65],"fuses":[66],"multi-scale":[67],"information":[69],"from":[70],"pre-trained":[71],"models.":[73],"Our":[74],"has":[76],"clear":[78],"concise":[80],"framework":[81,89],"networks.":[86],"With":[87],"this":[88],"extensive":[91],"augmentation":[93],"methods,":[94],"our":[95],"presented":[96],"achieves":[98],"false":[100,107],"reject":[101],"rate":[102,109],"3.85%":[104],"alarm":[108],"3.42%":[111],"on":[112],"far-field":[113],"in":[115,126],"development":[117],"set":[118],"competition":[121],"database,":[122],"which":[123],"ranks":[124],"2nd":[125],"track":[131],"challenge.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
