{"id":"https://openalex.org/W4392904296","doi":"https://doi.org/10.1109/icassp48485.2024.10446312","title":"Small-Footprint Convolutional Neural Network with Reduced Feature Map for Voice Activity Detection","display_name":"Small-Footprint Convolutional Neural Network with Reduced Feature Map for Voice Activity Detection","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904296","doi":"https://doi.org/10.1109/icassp48485.2024.10446312"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446312","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446312","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":"conference-paper","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/A5102631474","display_name":"Hwabyeong Chae","orcid":null},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]},{"id":"https://openalex.org/I2799891827","display_name":"Korea Post","ror":"https://ror.org/00p45d091","country_code":"KR","type":"government","lineage":["https://openalex.org/I2799891827","https://openalex.org/I2801339556","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hwabyeong Chae","raw_affiliation_strings":["POSTECH,Department of Electrical Engineering,Republic of Korea","Department of Electrical Engineering, POSTECH, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"POSTECH,Department of Electrical Engineering,Republic of Korea","institution_ids":["https://openalex.org/I2799891827"]},{"raw_affiliation_string":"Department of Electrical Engineering, POSTECH, Republic of Korea","institution_ids":["https://openalex.org/I123900574","https://openalex.org/I2799891827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048785540","display_name":"Sunggu Lee","orcid":"https://orcid.org/0000-0003-3858-0779"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]},{"id":"https://openalex.org/I2799891827","display_name":"Korea Post","ror":"https://ror.org/00p45d091","country_code":"KR","type":"government","lineage":["https://openalex.org/I2799891827","https://openalex.org/I2801339556","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sunggu Lee","raw_affiliation_strings":["POSTECH,Department of Electrical Engineering,Republic of Korea","Department of Electrical Engineering, POSTECH, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"POSTECH,Department of Electrical Engineering,Republic of Korea","institution_ids":["https://openalex.org/I2799891827"]},{"raw_affiliation_string":"Department of Electrical Engineering, POSTECH, Republic of Korea","institution_ids":["https://openalex.org/I123900574","https://openalex.org/I2799891827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8343,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67072173,"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":"12266","last_page":"12270"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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":0.9994999766349792,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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/memory-footprint","display_name":"Memory footprint","score":0.8949533700942993},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8332571387290955},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7159956693649292},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6619834899902344},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.6562082767486572},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6377784013748169},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5128962993621826},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.49391084909439087},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4771311283111572},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47475412487983704},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44521647691726685},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43311771750450134},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.13219180703163147}],"concepts":[{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.8949533700942993},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8332571387290955},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7159956693649292},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6619834899902344},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.6562082767486572},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6377784013748169},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5128962993621826},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.49391084909439087},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4771311283111572},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47475412487983704},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44521647691726685},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43311771750450134},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.13219180703163147},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/icassp48485.2024.10446312","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446312","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/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2020969069","https://openalex.org/W2033875152","https://openalex.org/W2181253919","https://openalex.org/W2746314669","https://openalex.org/W2791616807","https://openalex.org/W2797583228","https://openalex.org/W2885307078","https://openalex.org/W2936299888","https://openalex.org/W2936774411","https://openalex.org/W2963446712","https://openalex.org/W2963855133","https://openalex.org/W2974231335","https://openalex.org/W3007258144","https://openalex.org/W3042011474","https://openalex.org/W3160747466","https://openalex.org/W3161282967","https://openalex.org/W4296068967","https://openalex.org/W4372262623","https://openalex.org/W6676413359","https://openalex.org/W6743428213","https://openalex.org/W6750665317","https://openalex.org/W6767671539"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W3137434606","https://openalex.org/W4225315139","https://openalex.org/W4385881881","https://openalex.org/W4372263373","https://openalex.org/W3128402741","https://openalex.org/W2078418570"],"abstract_inverted_index":{"By":[0],"using":[1,97],"Voice":[2],"Activity":[3],"Detection":[4],"(VAD)":[5],"as":[6,83,113,120],"a":[7,34,46,72,98],"preprocessing":[8],"step,":[9],"hardware-efficient":[10],"implementations":[11],"are":[12],"possible":[13],"for":[14],"speech":[15],"applications":[16],"that":[17,41],"need":[18],"to":[19,60,82,125],"run":[20],"continuously":[21],"in":[22],"severely":[23],"resource-constrained":[24],"environments.":[25],"For":[26],"this":[27],"purpose,":[28],"we":[29],"propose":[30],"TinyVAD,":[31],"which":[32],"is":[33,89],"new":[35],"convolutional":[36,76],"neural":[37],"network":[38],"(CNN)":[39],"model":[40,88],"executes":[42,106],"extremely":[43],"efficiently":[44],"with":[45,78,93],"small":[47],"memory":[48],"footprint.":[49],"TinyVAD":[50,105],"uses":[51],"an":[52],"input":[53,66],"pixel":[54],"matrix":[55],"partitioning":[56],"method,":[57],"termed":[58],"patchify,":[59],"downscale":[61],"the":[62,65,126],"resolution":[63],"of":[64,74,101],"spectrogram.":[67],"The":[68,86],"hidden":[69],"layers":[70],"use":[71],"sequence":[73],"special":[75],"structures":[77],"bypass":[79],"links,":[80],"referred":[81],"CSPTiny":[84],"layers.":[85],"proposed":[87],"evaluated":[90],"and":[91,116],"compared":[92,124],"previous":[94,127],"VAD":[95],"methods":[96],"diverse":[99],"set":[100],"noisy":[102],"environmental":[103],"datasets.":[104],"3.13":[107],"times":[108],"faster,":[109],"utilizes":[110],"only":[111,118],"12.5%":[112],"many":[114,121],"multiplications,":[115],"requires":[117],"13.0%":[119],"parameters":[122],"when":[123],"state-of-the-art.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
