{"id":"https://openalex.org/W2165255420","doi":"https://doi.org/10.1109/ijcnn.2008.4634203","title":"Gaussian process regression for voice activity detection and speech enhancement","display_name":"Gaussian process regression for voice activity detection and speech enhancement","publication_year":2008,"publication_date":"2008-06-01","ids":{"openalex":"https://openalex.org/W2165255420","doi":"https://doi.org/10.1109/ijcnn.2008.4634203","mag":"2165255420"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2008.4634203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2008.4634203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)","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/A5086350199","display_name":"Sunho Park","orcid":"https://orcid.org/0000-0002-0388-2198"},"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"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Sunho Park","raw_affiliation_strings":["Department of Computer Science, Pohang University of Science and Technology, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Pohang University of Science and Technology, South Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066405061","display_name":"Seungjin Choi","orcid":"https://orcid.org/0000-0002-7873-4616"},"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"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seungjin Choi","raw_affiliation_strings":["Department of Computer Science, Pohang University of Science and Technology, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Pohang University of Science and Technology, South Korea","institution_ids":["https://openalex.org/I123900574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5086350199"],"corresponding_institution_ids":["https://openalex.org/I123900574"],"apc_list":null,"apc_paid":null,"fwci":1.1708,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.85602861,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"8","issue":null,"first_page":"2879","last_page":"2882"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9947999715805054,"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/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","score":0.9926000237464905,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.7643871903419495},{"id":"https://openalex.org/keywords/kriging","display_name":"Kriging","score":0.6716331243515015},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6666762828826904},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.6427165269851685},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6046061515808105},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5800326466560364},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5403379201889038},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.5212914943695068},{"id":"https://openalex.org/keywords/regression-analysis","display_name":"Regression analysis","score":0.5188354253768921},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5005350112915039},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.48753902316093445},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.46641620993614197},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4624384343624115},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.42643940448760986},{"id":"https://openalex.org/keywords/bayesian-linear-regression","display_name":"Bayesian linear regression","score":0.42630481719970703},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.35634845495224},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33131664991378784},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.30283892154693604},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.22767871618270874},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20903968811035156},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.16299957036972046},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.06853905320167542}],"concepts":[{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.7643871903419495},{"id":"https://openalex.org/C81692654","wikidata":"https://www.wikidata.org/wiki/Q225926","display_name":"Kriging","level":2,"score":0.6716331243515015},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6666762828826904},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6427165269851685},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6046061515808105},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5800326466560364},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5403379201889038},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.5212914943695068},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.5188354253768921},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5005350112915039},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.48753902316093445},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.46641620993614197},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4624384343624115},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.42643940448760986},{"id":"https://openalex.org/C37903108","wikidata":"https://www.wikidata.org/wiki/Q4874474","display_name":"Bayesian linear regression","level":4,"score":0.42630481719970703},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.35634845495224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33131664991378784},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.30283892154693604},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.22767871618270874},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20903968811035156},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.16299957036972046},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.06853905320167542},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/ijcnn.2008.4634203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2008.4634203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.331.972","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.331.972","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.postech.ac.kr/~seungjin/publications/ijcnn08_shpark.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1521843029","https://openalex.org/W1553274319","https://openalex.org/W1567512734","https://openalex.org/W1746819321","https://openalex.org/W1905983571","https://openalex.org/W1920741591","https://openalex.org/W1989337816","https://openalex.org/W1994005439","https://openalex.org/W1995536493","https://openalex.org/W2048510784","https://openalex.org/W2128653836","https://openalex.org/W2140977001","https://openalex.org/W2145585502","https://openalex.org/W2148628165","https://openalex.org/W2151381543","https://openalex.org/W2161767008","https://openalex.org/W2167090878","https://openalex.org/W4211049957","https://openalex.org/W4242974603","https://openalex.org/W6682192834","https://openalex.org/W6683852811"],"related_works":["https://openalex.org/W2022434169","https://openalex.org/W3154615872","https://openalex.org/W3022659297","https://openalex.org/W4327691454","https://openalex.org/W2883670420","https://openalex.org/W2165255420","https://openalex.org/W4206651436","https://openalex.org/W4309741541","https://openalex.org/W2094570066","https://openalex.org/W2144324444"],"abstract_inverted_index":{"Gaussian":[0],"process":[1],"(GP)":[2],"model":[3],"is":[4,11,79],"a":[5,23,37,47,58],"flexible":[6],"nonparametric":[7],"Bayesian":[8],"method":[9,25,61],"that":[10],"widely":[12],"used":[13],"in":[14,36,52,66,84],"regression":[15],"and":[16,33,74],"classification.":[17],"In":[18],"this":[19],"paper":[20],"we":[21,27],"present":[22],"probabilistic":[24],"where":[26],"solve":[28],"voice":[29],"activity":[30],"detection":[31],"(VAD)":[32],"speech":[34,45,78],"enhancement":[35],"single":[38],"framework":[39],"of":[40,92],"GP":[41,48,53,85],"regression,":[42],"modeling":[43],"clean":[44],"by":[46,81],"smoother.":[49],"Optimized":[50],"hyperparameters":[51],"models":[54],"lead":[55],"us":[56],"to":[57],"novel":[59],"VAD":[60],"since":[62],"learned":[63],"length-scale":[64],"parameters":[65],"covariance":[67],"functions":[68],"are":[69],"much":[70],"different":[71],"between":[72],"voiced":[73],"unvoiced":[75],"frames.":[76],"Clean":[77],"estimated":[80],"posterior":[82],"means":[83],"models.":[86],"Numerical":[87],"experiments":[88],"confirm":[89],"the":[90],"validity":[91],"our":[93],"method.":[94]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}