{"id":"https://openalex.org/W4392903780","doi":"https://doi.org/10.1109/icassp48485.2024.10446945","title":"SVAD: A Robust, Low-Power, and Light-Weight Voice Activity Detection with Spiking Neural Networks","display_name":"SVAD: A Robust, Low-Power, and Light-Weight Voice Activity Detection with Spiking Neural Networks","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903780","doi":"https://doi.org/10.1109/icassp48485.2024.10446945"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446945","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446945","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/A5100773498","display_name":"Yang Qu","orcid":"https://orcid.org/0000-0002-3714-1814"},"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":true,"raw_author_name":"Qu Yang","raw_affiliation_strings":["National University of Singapore,Singapore","National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042687758","display_name":"Qianhui Liu","orcid":"https://orcid.org/0000-0003-4396-8807"},"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":"Qianhui Liu","raw_affiliation_strings":["National University of Singapore,Singapore","National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341065","display_name":"Nan Li","orcid":"https://orcid.org/0000-0002-5852-2325"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nan Li","raw_affiliation_strings":["Tianjin University,Tianjin,China","Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071074013","display_name":"Meng Ge","orcid":"https://orcid.org/0000-0003-2017-4529"},"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":"Meng Ge","raw_affiliation_strings":["National University of Singapore,Singapore","National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072108662","display_name":"Zeyang Song","orcid":"https://orcid.org/0000-0003-0122-8704"},"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":"Zeyang Song","raw_affiliation_strings":["National University of Singapore,Singapore","National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"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"]},{"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":"Haizhou Li","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen (CUHK-Shenzhen),China","National University of Singapore, Singapore","The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen (CUHK-Shenzhen),China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), China","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100773498"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":2.87,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.90939121,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"221","last_page":"225"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9970999956130981,"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/robustness","display_name":"Robustness (evolution)","score":0.8093135356903076},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8049556016921997},{"id":"https://openalex.org/keywords/spiking-neural-network","display_name":"Spiking neural network","score":0.5632784962654114},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5186097621917725},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48853787779808044},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.46763136982917786},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4312066435813904},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3865917921066284},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3357304036617279}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8093135356903076},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8049556016921997},{"id":"https://openalex.org/C11731999","wikidata":"https://www.wikidata.org/wiki/Q9067355","display_name":"Spiking neural network","level":3,"score":0.5632784962654114},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5186097621917725},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48853787779808044},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.46763136982917786},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4312066435813904},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3865917921066284},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3357304036617279},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446945","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446945","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":[{"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"}],"funders":[{"id":"https://openalex.org/F4320320698","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1506438021","https://openalex.org/W1979974160","https://openalex.org/W2115717467","https://openalex.org/W2129120544","https://openalex.org/W2149053750","https://openalex.org/W2150355110","https://openalex.org/W2400845926","https://openalex.org/W2727244960","https://openalex.org/W2766195687","https://openalex.org/W2783525259","https://openalex.org/W2887734663","https://openalex.org/W2952218014","https://openalex.org/W2964052309","https://openalex.org/W2973127906","https://openalex.org/W2982265383","https://openalex.org/W2984844508","https://openalex.org/W2997498437","https://openalex.org/W3015305007","https://openalex.org/W3099330747","https://openalex.org/W3197727170","https://openalex.org/W4225278875","https://openalex.org/W4238614602","https://openalex.org/W4297841921","https://openalex.org/W4304731206","https://openalex.org/W4312555112","https://openalex.org/W4377371819","https://openalex.org/W4386083031","https://openalex.org/W4402778510","https://openalex.org/W6846765651","https://openalex.org/W6847215460","https://openalex.org/W6852962002","https://openalex.org/W6859383537"],"related_works":["https://openalex.org/W3126544799","https://openalex.org/W4390516098","https://openalex.org/W3104333581","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2542565870","https://openalex.org/W3111828357","https://openalex.org/W3018398156","https://openalex.org/W2142795561","https://openalex.org/W4391549771"],"abstract_inverted_index":{"Speech":[0],"applications":[1],"are":[2,27],"expected":[3],"to":[4,29,40,61,101],"be":[5,30],"low-power":[6],"and":[7,33,44,83,86,116,122],"robust":[8],"under":[9],"noisy":[10],"conditions.":[11],"An":[12],"effective":[13,77],"Voice":[14],"Activity":[15],"Detection":[16],"(VAD)":[17],"front-end":[18],"lowers":[19],"the":[20],"computational":[21],"need.":[22],"Spiking":[23,96],"Neural":[24,98],"Networks":[25,99],"(SNNs)":[26],"known":[28],"biologically":[31],"plausible":[32],"power-efficient.":[34],"However,":[35],"SNN-based":[36,57,71],"VADs":[37],"have":[38],"yet":[39],"achieve":[41],"noise":[42,88,114],"robustness":[43,89,115],"often":[45],"require":[46],"large":[47],"models":[48],"for":[49,131],"high":[50],"performance.":[51],"This":[52],"paper":[53],"introduces":[54],"a":[55,123,128],"novel":[56],"VAD":[58,133],"model,":[59],"referred":[60],"as":[62],"sVAD,":[63],"which":[64],"features":[65],"an":[66,70],"auditory":[67,78],"encoder":[68],"with":[69,90],"attention":[72,91],"mechanism.":[73],"Particularly,":[74],"it":[75,127],"provides":[76],"feature":[79],"representation":[80],"through":[81],"SincNet":[82],"1D":[84],"convolution,":[85],"improves":[87],"mechanisms.":[92],"The":[93],"classifier":[94],"utilizes":[95],"Recurrent":[97],"(sRNN)":[100],"exploit":[102],"temporal":[103],"speech":[104],"information.":[105],"Experimental":[106],"results":[107],"demonstrate":[108],"that":[109],"our":[110],"sVAD":[111],"achieves":[112],"remarkable":[113],"meanwhile":[117],"maintains":[118],"low":[119],"power":[120],"consumption":[121],"small":[124],"footprint,":[125],"making":[126],"promising":[129],"solution":[130],"real-world":[132],"applications.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
