{"id":"https://openalex.org/W2133938994","doi":"https://doi.org/10.1109/icassp.2009.4960658","title":"Using information theory to detect voice activity","display_name":"Using information theory to detect voice activity","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2133938994","doi":"https://doi.org/10.1109/icassp.2009.4960658","mag":"2133938994"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960658","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960658","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5109239522","display_name":"Fotios Talantzis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210162098","display_name":"Athens Information Technology","ror":"https://ror.org/05eqt7s39","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210162098"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Fotios Talantzis","raw_affiliation_strings":["Autonomic & Grid Computing Group, Athens Information Technology Center, Athens, Greece","Athens Information Technology, Autonomic & Grid Computing Group, 0.8km Markopoulo Av., 19002, Athens, Greece"],"affiliations":[{"raw_affiliation_string":"Autonomic & Grid Computing Group, Athens Information Technology Center, Athens, Greece","institution_ids":["https://openalex.org/I4210162098"]},{"raw_affiliation_string":"Athens Information Technology, Autonomic & Grid Computing Group, 0.8km Markopoulo Av., 19002, Athens, Greece","institution_ids":["https://openalex.org/I4210162098"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052125071","display_name":"A.G. Constantinides","orcid":"https://orcid.org/0000-0003-2946-5509"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Anthony G. Constantinides","raw_affiliation_strings":["Electrical & Electronic Engineering, Imperial College London, London, UK","Imperial College London, Electrical & Electronic Engineering, Exhibition Rd., SW72AZ, UK"],"affiliations":[{"raw_affiliation_string":"Electrical & Electronic Engineering, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Imperial College London, Electrical & Electronic Engineering, Exhibition Rd., SW72AZ, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5109239522"],"corresponding_institution_ids":["https://openalex.org/I4210162098"],"apc_list":null,"apc_paid":null,"fwci":0.7142,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.70543767,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4613","last_page":"4616"},"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":0.9973000288009644,"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/T11309","display_name":"Music and Audio Processing","score":0.9958000183105469,"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/reverberation","display_name":"Reverberation","score":0.8976510763168335},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.706770658493042},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7046424746513367},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.6260933876037598},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5909332036972046},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5698776841163635},{"id":"https://openalex.org/keywords/ambient-noise-level","display_name":"Ambient noise level","score":0.5268558263778687},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4874253571033478},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4707898497581482},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.47030800580978394},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.43437108397483826},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4281395375728607},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.42178207635879517},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35320815443992615},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.23360049724578857},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.19994065165519714},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.16381779313087463},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.15041154623031616},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12840086221694946},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.127234548330307},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09820815920829773}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.8976510763168335},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.706770658493042},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7046424746513367},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.6260933876037598},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5909332036972046},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5698776841163635},{"id":"https://openalex.org/C205312793","wikidata":"https://www.wikidata.org/wiki/Q16002801","display_name":"Ambient noise level","level":3,"score":0.5268558263778687},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4874253571033478},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4707898497581482},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.47030800580978394},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.43437108397483826},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4281395375728607},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.42178207635879517},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35320815443992615},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.23360049724578857},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.19994065165519714},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.16381779313087463},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.15041154623031616},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12840086221694946},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.127234548330307},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09820815920829773},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2009.4960658","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960658","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.990.3251","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.990.3251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mirlab.org/conference_papers/International_Conference/ICASSP%202009/pdfs/0004613.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7599999904632568,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2025331211","https://openalex.org/W2046317813","https://openalex.org/W2098265087","https://openalex.org/W2098441927","https://openalex.org/W2105137818","https://openalex.org/W2144584285"],"related_works":["https://openalex.org/W2037659933","https://openalex.org/W4256175191","https://openalex.org/W2770624987","https://openalex.org/W3081244242","https://openalex.org/W166591803","https://openalex.org/W2898451895","https://openalex.org/W2553161202","https://openalex.org/W1186493362","https://openalex.org/W2418631473","https://openalex.org/W2081359368"],"abstract_inverted_index":{"Voice":[0],"activity":[1,47],"detection":[2,48],"systems":[3,14,31],"attempt":[4],"to":[5,25,55,82],"discriminate":[6],"between":[7,57],"voice":[8,46],"and":[9,20,36,62,91],"other":[10],"ambient":[11],"sounds.":[12],"Most":[13],"use":[15],"a":[16,58],"single":[17],"microphone":[18],"approach":[19],"rely":[21],"on":[22,34,104],"training":[23],"prior":[24],"employment.":[26],"The":[27],"performance":[28,97],"of":[29,53,66,70,89,98],"these":[30],"relies":[32],"heavily":[33],"reverberation":[35,90],"noise":[37,65],"levels.":[38],"In":[39],"this":[40],"paper":[41],"we":[42],"present":[43],"an":[44,75],"unsupervised":[45],"system":[49,100,118],"that":[50,79,115],"uses":[51],"pairs":[52],"microphones":[54],"discern":[56],"coherent":[59],"acoustic":[60],"source":[61],"spatially":[63],"diffuse":[64],"low":[67],"coherence.":[68],"Measurement":[69],"coherency":[71],"is":[72,101,113],"performed":[73],"using":[74],"information":[76],"theoretic":[77],"metric":[78],"integrates":[80],"means":[81],"filter":[83],"out":[84],"more":[85,120],"effectively":[86],"the":[87,96,99,105,109,116],"effect":[88],"noise.":[92],"Using":[93],"extensive":[94],"experiments,":[95],"investigated.":[102],"Based":[103],"conditions":[106],"imposed":[107],"by":[108],"experimental":[110],"environments":[111],"it":[112],"shown":[114],"proposed":[117],"remains":[119],"robust":[121],"than":[122],"its":[123],"counterparts":[124],"in":[125],"all":[126],"cases.":[127]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
