{"id":"https://openalex.org/W4392910573","doi":"https://doi.org/10.1109/icassp48485.2024.10446074","title":"Robust Wake Word Spotting With Frame-Level Cross-Modal Attention Based Audio-Visual Conformer","display_name":"Robust Wake Word Spotting With Frame-Level Cross-Modal Attention Based Audio-Visual Conformer","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910573","doi":"https://doi.org/10.1109/icassp48485.2024.10446074"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446074","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoxu Wang","raw_affiliation_strings":["Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems,Kunshan,China","Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China"],"affiliations":[{"raw_affiliation_string":"Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems,Kunshan,China","institution_ids":["https://openalex.org/I4210159968"]},{"raw_affiliation_string":"Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035358464","display_name":"Ming Cheng","orcid":"https://orcid.org/0000-0002-3466-234X"},"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":"Ming Cheng","raw_affiliation_strings":["Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems,Kunshan,China","Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China"],"affiliations":[{"raw_affiliation_string":"Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems,Kunshan,China","institution_ids":["https://openalex.org/I4210159968"]},{"raw_affiliation_string":"Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, 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/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Fu","raw_affiliation_strings":["Zhejiang Laboratory,Research Center for Intelligent Robotics, Research Institute of Interdisciplinary Innovation,Hangzhou,China","Research Center for Intelligent Robotics, Research Institute of Interdisciplinary Innovation, Zhejiang Laboratory, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Laboratory,Research Center for Intelligent Robotics, Research Institute of Interdisciplinary Innovation,Hangzhou,China","institution_ids":["https://openalex.org/I4210123185"]},{"raw_affiliation_string":"Research Center for Intelligent Robotics, Research Institute of Interdisciplinary Innovation, Zhejiang Laboratory, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"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/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":["Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems,Kunshan,China","Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China"],"affiliations":[{"raw_affiliation_string":"Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems,Kunshan,China","institution_ids":["https://openalex.org/I4210159968"]},{"raw_affiliation_string":"Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, 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/A5016797242"],"corresponding_institution_ids":["https://openalex.org/I4210159968"],"apc_list":null,"apc_paid":null,"fwci":1.5001,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.80806296,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"11556","last_page":"11560"},"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":0.9987999796867371,"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":0.9977999925613403,"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":0.8837448954582214},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7968840599060059},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6734721064567566},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.6616859436035156},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.6356152296066284},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6271302700042725},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5433794260025024},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5393618941307068},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47214725613594055},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07383778691291809}],"concepts":[{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.8837448954582214},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7968840599060059},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6734721064567566},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.6616859436035156},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.6356152296066284},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6271302700042725},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5433794260025024},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5393618941307068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47214725613594055},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07383778691291809},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446074","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307500","display_name":"Youth Foundation","ror":null},{"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2407023693","https://openalex.org/W2748659049","https://openalex.org/W2897492880","https://openalex.org/W2936774411","https://openalex.org/W2969985801","https://openalex.org/W3034552680","https://openalex.org/W3035422918","https://openalex.org/W3094700205","https://openalex.org/W3162293946","https://openalex.org/W3163237592","https://openalex.org/W3163527109","https://openalex.org/W3182657421","https://openalex.org/W3207570488","https://openalex.org/W3209059054","https://openalex.org/W4224213421","https://openalex.org/W4224916427","https://openalex.org/W4224916733","https://openalex.org/W4224933780","https://openalex.org/W4224940398","https://openalex.org/W4283014400","https://openalex.org/W4297841411","https://openalex.org/W4297841641","https://openalex.org/W4297841644","https://openalex.org/W4319300051","https://openalex.org/W4319862656","https://openalex.org/W4372270419","https://openalex.org/W4375869136","https://openalex.org/W6782374147"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W4286904253","https://openalex.org/W3119978414","https://openalex.org/W2516975559","https://openalex.org/W3206647229","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2545741539","https://openalex.org/W1989658893"],"abstract_inverted_index":{"In":[0,58],"recent":[1],"years,":[2],"neural":[3],"network-based":[4],"Wake":[5,21],"Word":[6,22],"Spotting":[7,23],"achieves":[8,120],"good":[9],"performance":[10,74,107],"on":[11,128],"clean":[12],"audio":[13],"samples":[14],"but":[15],"struggles":[16],"in":[17],"noisy":[18],"environments.":[19],"Audio-Visual":[20,101],"(AVWWS)":[24],"receives":[25],"lots":[26],"of":[27,75],"attention":[28],"because":[29],"visual":[30],"lip":[31,90],"movement":[32],"information":[33,84],"is":[34],"not":[35],"affected":[36],"by":[37,108],"complex":[38],"acoustic":[39],"scenes.":[40],"Previous":[41],"works":[42],"usually":[43],"use":[44],"simple":[45],"addition":[46],"or":[47],"concatenation":[48],"for":[49,113],"multi-modal":[50,83],"fusion.":[51],"The":[52,117],"inter-modal":[53],"correlation":[54],"remains":[55],"relatively":[56],"under-explored.":[57],"this":[59],"paper,":[60],"we":[61],"propose":[62],"a":[63,121],"novel":[64],"module":[65,79],"called":[66],"Frame-Level":[67],"Cross-Modal":[68],"Attention":[69],"(FLCMA)":[70],"to":[71],"improve":[72,105],"the":[73,86,97,106,114,129],"AVWWS":[76,115],"systems.":[77],"This":[78],"can":[80],"help":[81],"model":[82],"at":[85],"frame-level":[87],"through":[88],"synchronous":[89],"movements":[91],"and":[92,103],"speech":[93],"signals.":[94],"We":[95],"train":[96],"end-to-end":[98],"FLCMA":[99],"based":[100],"Conformer":[102],"further":[104],"fine-tuning":[109],"pre-trained":[110],"uni-modal":[111],"models":[112],"task.":[116],"proposed":[118],"system":[119],"new":[122],"state-of-the-art":[123],"result":[124],"(4.57%":[125],"WWS":[126],"score)":[127],"far-field":[130],"MISP":[131],"dataset.":[132]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2025-12-05T23:21:25.405358","created_date":"2025-10-10T00:00:00"}