{"id":"https://openalex.org/W2099439858","doi":"https://doi.org/10.1109/icassp.2012.6287874","title":"Sparse power spectrum based robust voice activity detector","display_name":"Sparse power spectrum based robust voice activity detector","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2099439858","doi":"https://doi.org/10.1109/icassp.2012.6287874","mag":"2099439858"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6287874","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6287874","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 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/A5005904745","display_name":"Datao You","orcid":"https://orcid.org/0000-0001-5968-4994"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Datao You","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","School of Computer Science and Technology, Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101508830","display_name":"Jiqing Han","orcid":"https://orcid.org/0000-0002-4297-4300"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiqing Han","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","School of Computer Science and Technology, Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041058909","display_name":"Guibin Zheng","orcid":"https://orcid.org/0000-0002-4280-5224"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guibin Zheng","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","School of Computer Science and Technology, Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101846141","display_name":"Tieran Zheng","orcid":"https://orcid.org/0009-0006-5179-0278"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tieran Zheng","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","School of Computer Science and Technology, Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5005904745"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":3.4279,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.94632296,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"139","issue":null,"first_page":"289","last_page":"292"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9991000294685364,"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/detector","display_name":"Detector","score":0.7233651876449585},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6957427263259888},{"id":"https://openalex.org/keywords/spectrum","display_name":"Spectrum (functional analysis)","score":0.6149821877479553},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.555879533290863},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5454469919204712},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.5353864431381226},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.4989004135131836},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44951653480529785},{"id":"https://openalex.org/keywords/spectral-density","display_name":"Spectral density","score":0.44630876183509827},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4302462339401245},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.43012282252311707},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.423355370759964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39847686886787415},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3721435070037842},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.21948254108428955},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12180754542350769},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07398366928100586},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.058853209018707275}],"concepts":[{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.7233651876449585},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6957427263259888},{"id":"https://openalex.org/C156778621","wikidata":"https://www.wikidata.org/wiki/Q1365748","display_name":"Spectrum (functional analysis)","level":2,"score":0.6149821877479553},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.555879533290863},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5454469919204712},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.5353864431381226},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.4989004135131836},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44951653480529785},{"id":"https://openalex.org/C168110828","wikidata":"https://www.wikidata.org/wiki/Q1331626","display_name":"Spectral density","level":2,"score":0.44630876183509827},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4302462339401245},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.43012282252311707},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.423355370759964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39847686886787415},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3721435070037842},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.21948254108428955},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12180754542350769},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07398366928100586},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.058853209018707275},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2012.6287874","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6287874","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1965559434","https://openalex.org/W2005082281","https://openalex.org/W2005876975","https://openalex.org/W2034260606","https://openalex.org/W2098265087","https://openalex.org/W2104132386","https://openalex.org/W2112994876","https://openalex.org/W2120077739","https://openalex.org/W2123550723","https://openalex.org/W2126693545","https://openalex.org/W2129120544","https://openalex.org/W2140609183","https://openalex.org/W2159856503","https://openalex.org/W2535438430","https://openalex.org/W3105340263","https://openalex.org/W3145636786"],"related_works":["https://openalex.org/W1630865680","https://openalex.org/W4214692512","https://openalex.org/W2373767407","https://openalex.org/W2516933085","https://openalex.org/W3168109306","https://openalex.org/W2130187411","https://openalex.org/W2387058352","https://openalex.org/W2004814108","https://openalex.org/W3098723682","https://openalex.org/W2118992737"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,37,43,59,80],"robust":[4],"approach":[5,100],"to":[6,61,82],"improve":[7],"the":[8,53,63,91,98,103],"performance":[9,104],"of":[10,45,105],"voice":[11],"activity":[12],"detector":[13],"(VAD)":[14],"in":[15,107],"low":[16,108],"signal-to-noise":[17],"ratio":[18],"(SNR)":[19],"noisy":[20,110],"environments.":[21,111],"To":[22],"this":[23],"end,":[24],"we":[25,56,78],"first":[26],"generate":[27],"sparse":[28,34,49,54,74],"representations":[29],"by":[30],"Bregman":[31],"Iteration":[32],"based":[33,89],"decomposition":[35],"with":[36],"learned":[38],"over-complete":[39],"dictionary,":[40],"and":[41,68,86],"derive":[42],"kind":[44],"audio":[46],"feature":[47],"called":[48],"power":[50,75],"spectrum":[51,67,72],"from":[52,73],"representations.":[55],"then":[57],"propose":[58],"method":[60],"calculate":[62],"short":[64],"segment":[65,70],"average":[66,71,93],"long":[69],"spectrum.":[76,94],"Finally,":[77],"design":[79],"criterion":[81],"detect":[83],"speech":[84],"region":[85,88],"non-speech":[87],"on":[90],"above":[92],"Experiments":[95],"show":[96],"that":[97],"proposed":[99],"further":[101],"improves":[102],"VAD":[106],"SNR":[109]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
