{"id":"https://openalex.org/W2152472098","doi":"https://doi.org/10.1109/icassp.2003.1198923","title":"Speech enhancement using blind source separation and two-channel energy based speaker detection","display_name":"Speech enhancement using blind source separation and two-channel energy based speaker detection","publication_year":2003,"publication_date":"2003-11-20","ids":{"openalex":"https://openalex.org/W2152472098","doi":"https://doi.org/10.1109/icassp.2003.1198923","mag":"2152472098"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1198923","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198923","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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/A5009801065","display_name":"Erik Visser","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"E. Visser","raw_affiliation_strings":["Institute for Neural Computation, University of California, San Diego La Jolla, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Neural Computation, University of California, San Diego La Jolla, CA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056269350","display_name":"Te-Won Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Te-Won Lee","raw_affiliation_strings":["Institute for Neural Computation, University of California, San Diego La Jolla, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Neural Computation, University of California, San Diego La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"884"},"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/T11447","display_name":"Blind Source Separation Techniques","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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9908999800682068,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7211040258407593},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.7143262624740601},{"id":"https://openalex.org/keywords/wiener-filter","display_name":"Wiener filter","score":0.689751923084259},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6860702037811279},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6731203198432922},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5889840126037598},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5706547498703003},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.5705577731132507},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5545288920402527},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.5188294649124146},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5135205388069153},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.5027666091918945},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.492605984210968},{"id":"https://openalex.org/keywords/noise-power","display_name":"Noise power","score":0.4921113848686218},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.46982431411743164},{"id":"https://openalex.org/keywords/inverse-filter","display_name":"Inverse filter","score":0.4195464551448822},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.4153202772140503},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29941657185554504},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.2834343910217285},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17492690682411194},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.15580710768699646},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0996088981628418},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07986265420913696},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.07077091932296753},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06860461831092834}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7211040258407593},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.7143262624740601},{"id":"https://openalex.org/C18537770","wikidata":"https://www.wikidata.org/wiki/Q25523","display_name":"Wiener filter","level":2,"score":0.689751923084259},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6860702037811279},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6731203198432922},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5889840126037598},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5706547498703003},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.5705577731132507},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5545288920402527},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.5188294649124146},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5135205388069153},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.5027666091918945},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.492605984210968},{"id":"https://openalex.org/C203234222","wikidata":"https://www.wikidata.org/wiki/Q2133519","display_name":"Noise power","level":3,"score":0.4921113848686218},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.46982431411743164},{"id":"https://openalex.org/C2779948431","wikidata":"https://www.wikidata.org/wiki/Q17092649","display_name":"Inverse filter","level":3,"score":0.4195464551448822},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.4153202772140503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29941657185554504},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.2834343910217285},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17492690682411194},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.15580710768699646},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0996088981628418},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07986265420913696},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.07077091932296753},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06860461831092834},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"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/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.2003.1198923","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198923","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":9,"referenced_works":["https://openalex.org/W79317937","https://openalex.org/W204466630","https://openalex.org/W1994630425","https://openalex.org/W2096779346","https://openalex.org/W2108384452","https://openalex.org/W2128911505","https://openalex.org/W2129120544","https://openalex.org/W6603280604","https://openalex.org/W6608353156"],"related_works":["https://openalex.org/W2106793170","https://openalex.org/W1577562165","https://openalex.org/W2276822462","https://openalex.org/W2028846388","https://openalex.org/W4295210860","https://openalex.org/W2438843077","https://openalex.org/W2369650530","https://openalex.org/W2386806647","https://openalex.org/W3168171120","https://openalex.org/W2161534637"],"abstract_inverted_index":{"A":[0],"speech":[1,33,116],"enhancement":[2],"scheme":[3],"is":[4,59,75,113],"presented":[5],"integrating":[6],"spatial":[7],"and":[8,126,131],"temporal":[9],"signal":[10,100],"processing":[11,64],"methods":[12],"for":[13,85],"blind":[14],"denoising":[15,134],"in":[16,61],"non":[17],"stationary":[18],"noise":[19,58,125],"environments.":[20],"In":[21],"a":[22,40,48,62,78],"first":[23],"stage,":[24],"spatially":[25],"localized":[26],"point":[27],"sources":[28,53],"are":[29,89],"separated":[30,103],"from":[31,91,106],"noisy":[32],"signals":[34,105],"recorded":[35],"by":[36,97,115,123],"two":[37],"microphones":[38],"using":[39],"Blind":[41],"Source":[42],"Separation":[43],"(BSS)":[44],"algorithm":[45],"assuming":[46],"no":[47],"priori":[49],"knowledge":[50],"about":[51],"the":[52,67,72,86,107],"involved.":[54],"Spatially":[55],"distributed":[56],"background":[57],"removed":[60],"second":[63],"step.":[65],"Here,":[66],"BSS":[68,108],"output":[69],"channel":[70,133],"containing":[71],"desired":[73,92],"speaker":[74,93],"filtered":[76],"with":[77],"time-varying":[79],"Wiener":[80],"filter.":[81],"Noise":[82],"power":[83],"estimates":[84],"filter":[87],"coefficients":[88],"computed":[90],"absent":[94],"time-intervals":[95],"identified":[96],"comparing":[98],"only":[99],"energy":[101],"of":[102],"source":[104],"stage.":[109],"The":[110],"scheme's":[111],"performance":[112],"illustrated":[114],"recognition":[117],"experiments":[118],"on":[119],"real":[120],"recordings":[121],"corrupted":[122],"babble":[124],"compared":[127],"to":[128],"conventional":[129],"beamforming":[130],"single":[132],"techniques.":[135]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}