{"id":"https://openalex.org/W4411551478","doi":"https://doi.org/10.1109/tc.2025.3582069","title":"Human-Inspired Computing for Robust and Efficient Audio-Visual Speech Recognition","display_name":"Human-Inspired Computing for Robust and Efficient Audio-Visual Speech Recognition","publication_year":2025,"publication_date":"2025-06-23","ids":{"openalex":"https://openalex.org/W4411551478","doi":"https://doi.org/10.1109/tc.2025.3582069"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2025.3582069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2025.3582069","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-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/A5065911896","display_name":"Qianhui Liu","orcid":"https://orcid.org/0000-0003-1841-0940"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]},{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Qianhui Liu","raw_affiliation_strings":["School of Artificial Intelligence, Shandong University, Jinan, China","Department of Electrical and Computer Engineering, National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-1841-0940","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiadong Wang","orcid":"https://orcid.org/0000-0001-9372-3133"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jiadong Wang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore","Department of Electrical and Computer Engineering, National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-9372-3133","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yang Wang","orcid":"https://orcid.org/0000-0003-3369-6772"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Wang","raw_affiliation_strings":["School of Computer Science and Technology, Dalian University of Technology, Dalian, China","School of Computer Science and Technology, Dalian University of Technology, Liaoning, China"],"raw_orcid":"https://orcid.org/0000-0003-3369-6772","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Liaoning, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xin Yang","orcid":"https://orcid.org/0000-0002-8046-722X"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Yang","raw_affiliation_strings":["School of Computer Science and Technology, Dalian University of Technology, Dalian, China","School of Computer Science and Technology, Dalian University of Technology, Liaoning, China"],"raw_orcid":"https://orcid.org/0000-0002-8046-722X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Liaoning, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Gang Pan","orcid":"https://orcid.org/0000-0002-4049-6181"},"institutions":[{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Pan","raw_affiliation_strings":["State Key Lab of Brain-Machine Intelligence, College of Computer Science and Technology, MOE Frontier Science Center for Brain Science and Brain-Machine Integration, Zhejiang University, Hangzhou, China","College of Computer Science, Zhejiang University, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-4049-6181","affiliations":[{"raw_affiliation_string":"State Key Lab of Brain-Machine Intelligence, College of Computer Science and Technology, MOE Frontier Science Center for Brain Science and Brain-Machine Integration, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4210097554"]},{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["School of Data Science, The Chinese University of Hong Kong, Shenzhen, China","School of Data Science, the Chinese University of Hong Kong (Shenzhen), Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0001-9158-9401","affiliations":[{"raw_affiliation_string":"School of Data Science, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"School of Data Science, the Chinese University of Hong Kong (Shenzhen), Guangdong, China","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9024,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.72918355,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"74","issue":"9","first_page":"2950","last_page":"2961"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.7835000157356262,"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":0.7835000157356262,"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/T11439","display_name":"Video Analysis and Summarization","score":0.6991000175476074,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.6766999959945679,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.7656039595603943},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.747900128364563},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4610511362552643},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44285649061203003},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4265856444835663},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4249805212020874},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33946913480758667},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.11421588063240051}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7656039595603943},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.747900128364563},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4610511362552643},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44285649061203003},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4265856444835663},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4249805212020874},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33946913480758667},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.11421588063240051}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2025.3582069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2025.3582069","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2509497248","display_name":null,"funder_award_id":"I2001E0053","funder_id":"https://openalex.org/F4320320698","funder_display_name":"National University of Singapore"},{"id":"https://openalex.org/G3775886161","display_name":null,"funder_award_id":"61925603","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320320698","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W15147940","https://openalex.org/W1999085092","https://openalex.org/W2047480366","https://openalex.org/W2081144555","https://openalex.org/W2081297346","https://openalex.org/W2133804059","https://openalex.org/W2164653071","https://openalex.org/W2594690981","https://openalex.org/W2621826044","https://openalex.org/W2890952074","https://openalex.org/W2936979094","https://openalex.org/W2990793844","https://openalex.org/W3010748916","https://openalex.org/W3011234510","https://openalex.org/W3014674005","https://openalex.org/W3040838455","https://openalex.org/W3161932608","https://openalex.org/W3162072286","https://openalex.org/W3174822600","https://openalex.org/W3188021906","https://openalex.org/W4225278875","https://openalex.org/W4283324956","https://openalex.org/W4285819798","https://openalex.org/W4290712013","https://openalex.org/W4292574980","https://openalex.org/W4297841921","https://openalex.org/W4312340502","https://openalex.org/W4365790697","https://openalex.org/W4367663352","https://openalex.org/W4377564670","https://openalex.org/W4379251221","https://openalex.org/W4385815549","https://openalex.org/W4387917764","https://openalex.org/W4388691623","https://openalex.org/W4391116744","https://openalex.org/W4392487628","https://openalex.org/W4392903780","https://openalex.org/W4392904039","https://openalex.org/W4392909318","https://openalex.org/W4392928956","https://openalex.org/W4396732977","https://openalex.org/W4404788303","https://openalex.org/W4407008833","https://openalex.org/W6844652965"],"related_works":["https://openalex.org/W191108438","https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W249088392","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2559837139","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"Humans":[0],"excel":[1],"at":[2],"audiovisual":[3],"speech":[4,76,117],"recognition":[5,67],"(AVSR),":[6],"motivating":[7],"the":[8,24,128,171,190],"development":[9],"of":[10,131],"human-inspired":[11,83,198],"computing":[12,91],"for":[13,87],"robust":[14],"and":[15,57,69,97,136,144,193],"efficient":[16],"AVSR":[17,36,178],"models.":[18],"Spiking":[19],"neural":[20],"networks":[21],"(SNNs),":[22],"mimicking":[23],"brain\u2019s":[25],"information-processing":[26],"mechanisms,":[27],"offer":[28],"a":[29,81,105],"promising":[30],"foundation.":[31],"However,":[32],"research":[33],"on":[34,44,63,175],"SNN-based":[35],"remains":[37],"limited,":[38],"with":[39,133],"most":[40],"audio-visual":[41,134,185],"methods":[42,50],"focusing":[43],"object":[45],"or":[46],"digit":[47],"recognition.":[48],"These":[49],"oversimplify":[51],"multimodal":[52],"fusion,":[53],"neglecting":[54],"modality-specific":[55],"characteristics":[56],"interactions.":[58],"Additionally,":[59],"they":[60],"often":[61],"rely":[62],"future":[64],"information,":[65],"increasing":[66],"latency":[68],"limiting":[70],"real-time":[71],"applicability.":[72],"Inspired":[73],"by":[74],"human":[75,172],"perception,":[77],"this":[78],"paper":[79],"proposes":[80],"novel":[82],"SNN":[84,132,186],"named":[85],"HI-AVSNN":[86],"AVSR,":[88],"incorporating":[89],"three":[90],"characteristics:":[92],"spike":[93,150],"activity,":[94,151],"cueing":[95,101],"interaction,":[96,102],"causal":[98,124],"processing.":[99],"For":[100,123,149],"we":[103,126,156],"introduce":[104],"Spike-Driven":[106],"Visual-Cued":[107],"Speech":[108],"Processing":[109],"(sVCSP)":[110],"scheme,":[111],"where":[112],"visual":[113,168],"features":[114],"hierarchically":[115],"guide":[116],"processing":[118],"to":[119,140,154,160],"enhance":[120],"critical":[121],"features.":[122],"processing,":[125],"align":[127],"temporal":[129,138],"dimensions":[130],"inputs":[135],"apply":[137],"masking":[139],"ensure":[141],"only":[142],"past":[143],"current":[145],"information":[146],"is":[147],"used.":[148],"in":[152],"addition":[153],"SNNs,":[155],"incorporate":[157],"event":[158],"cameras":[159],"capture":[161],"lip":[162],"movements":[163],"as":[164],"spikes,":[165],"efficiently":[166],"encoding":[167],"data":[169],"like":[170],"retina.":[173],"Experiments":[174],"two":[176],"event-based":[177],"datasets":[179],"demonstrate":[180],"our":[181,197],"method":[182],"outperforms":[183],"existing":[184],"fusion":[187],"techniques,":[188],"showcasing":[189],"effectiveness,":[191],"robustness,":[192],"efficiency":[194],"achieved":[195],"through":[196],"computing.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
