{"id":"https://openalex.org/W2409196835","doi":null,"title":"Estimating uncertainty models for speech source localization in real-world environments","display_name":"Estimating uncertainty models for speech source localization in real-world environments","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2409196835","mag":"2409196835"},"language":"en","primary_location":{"id":"mag:2409196835","doi":null,"is_oa":false,"landing_page_url":"https://dspace.mit.edu/handle/1721.1/38227","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"dissertation","indexed_in":[],"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/A5029105520","display_name":"Trevor Darrell","orcid":"https://orcid.org/0000-0001-5453-8533","observed_orcids":["https://orcid.org/0000-0001-5453-8533"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trevor Darrell","raw_affiliation_strings":["Massachusetts Institute Of Technology#TAB#"],"raw_orcid":"https://orcid.org/0000-0001-5453-8533","affiliations":[{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023061955","display_name":"Kirk Wilson","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Wilson","raw_affiliation_strings":["Massachusetts Institute Of Technology#TAB#"],"raw_orcid":"https://orcid.org/0000-0001-9141-2219","affiliations":[{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9980000257492065,"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":0.9980000257492065,"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/T11309","display_name":"Music and Audio Processing","score":0.000699999975040555,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-source-localization","display_name":"speech localization","score":0.8759999871253967},{"id":"https://openalex.org/keywords/speech-separation","display_name":"speech separation","score":0.9570000171661377},{"id":"https://openalex.org/keywords/reverberation","display_name":"reverberation","score":0.6759999990463257},{"id":"https://openalex.org/keywords/generalized-cross-correlation","display_name":"generalized cross-correlation","score":0.8379999995231628},{"id":"https://openalex.org/keywords/time-delay-estimation","display_name":"time delay estimation","score":0.996999979019165},{"id":"https://openalex.org/keywords/uncertainty-modeling","display_name":"uncertainty modeling","score":0.46399998664855957},{"id":"https://openalex.org/keywords/speech-spectrograms","display_name":"speech spectrograms","score":0.6909999847412109},{"id":"https://openalex.org/keywords/precedence-effect","display_name":"precedence effect","score":0.8209999799728394},{"id":"https://openalex.org/keywords/generative-probabilistic-models","display_name":"probabilistic generative models","score":0.8289999961853027}],"concepts":[{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.7850762605667114},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.7134791612625122},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.62611323595047},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6066800355911255},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5508341193199158},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5418887734413147},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5392166376113892},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4829218089580536},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.48109692335128784},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.47470584511756897},{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.44715145230293274},{"id":"https://openalex.org/C9940772","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Psychoacoustics","level":3,"score":0.43403393030166626},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.4101671278476715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34913021326065063},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.19600042700767517},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.15305861830711365},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","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},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2409196835","doi":null,"is_oa":false,"landing_page_url":"https://dspace.mit.edu/handle/1721.1/38227","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W86821137","https://openalex.org/W126779258","https://openalex.org/W165586310","https://openalex.org/W196844030","https://openalex.org/W598425403","https://openalex.org/W1506558619","https://openalex.org/W1546892833","https://openalex.org/W1555217905","https://openalex.org/W1571275348","https://openalex.org/W1578856370","https://openalex.org/W1581848821","https://openalex.org/W1582904311","https://openalex.org/W1589179377","https://openalex.org/W1608844340","https://openalex.org/W1681324445","https://openalex.org/W1766888123","https://openalex.org/W1819207621","https://openalex.org/W1902027874","https://openalex.org/W1964538581","https://openalex.org/W1967845942","https://openalex.org/W1973990950","https://openalex.org/W1989337816","https://openalex.org/W1989866124","https://openalex.org/W1990835870","https://openalex.org/W1991139021","https://openalex.org/W1992635574","https://openalex.org/W1999955319","https://openalex.org/W2005228249","https://openalex.org/W2045352743","https://openalex.org/W2046317813","https://openalex.org/W2049633694","https://openalex.org/W2054377514","https://openalex.org/W2059344499","https://openalex.org/W2065691163","https://openalex.org/W2071489795","https://openalex.org/W2079237043","https://openalex.org/W2084347883","https://openalex.org/W2084458166","https://openalex.org/W2093225945","https://openalex.org/W2096439661","https://openalex.org/W2103780312","https://openalex.org/W2106071216","https://openalex.org/W2109349638","https://openalex.org/W2110429782","https://openalex.org/W2113374105","https://openalex.org/W2121973264","https://openalex.org/W2122635992","https://openalex.org/W2126341088","https://openalex.org/W2129901640","https://openalex.org/W2135080377","https://openalex.org/W2137988753","https://openalex.org/W2143169494","https://openalex.org/W2146053319","https://openalex.org/W2162654459","https://openalex.org/W2167314872","https://openalex.org/W2168221202","https://openalex.org/W2168793898","https://openalex.org/W2169183548","https://openalex.org/W2206680703","https://openalex.org/W2252839440","https://openalex.org/W2474646974","https://openalex.org/W2798909945","https://openalex.org/W3143596294"],"related_works":["https://openalex.org/W2159224462","https://openalex.org/W2106071216","https://openalex.org/W2019492707","https://openalex.org/W2118869960","https://openalex.org/W2121829303","https://openalex.org/W1552302901","https://openalex.org/W7099933071","https://openalex.org/W2129171989","https://openalex.org/W7026685811","https://openalex.org/W2171127352"],"abstract_inverted_index":{"This":[0,41],"thesis":[1],"develops":[2,24],"unproved":[3],"solutions":[4],"to":[5,57,84,129],"the":[6,33,47,51,65,74,85,88,96],"problems":[7],"of":[8,53,73,76,87,102,108,121,158],"audio":[9],"source":[10,14,21,92,132,136,139],"localization":[11,60,109,114,137],"and":[12,28,124,138,152],"speech":[13,48,77,122,131],"separation":[15],"in":[16,67,78,155],"real":[17,151],"reverberant":[18],"environments.":[19,160],"For":[20,91,134],"localization,":[22],"it":[23],"a":[25,54,79,103,118,156],"new":[26],"time-":[27],"frequency-dependent":[29],"weighting":[30,42,98],"function":[31,43,99],"for":[32,37],"generalized":[34],"cross-correlation":[35],"framework":[36],"time":[38],"delay":[39],"estimation.":[40],"is":[44,82],"derived":[45],"from":[46],"spectrogram":[49],"as":[50,100],"result":[52],"transformation":[55],"designed":[56],"optimally":[58],"predict":[59],"cue":[61,115],"accuracy.":[62],"By":[63],"structuring":[64],"problem":[66],"this":[68,113,126],"way,":[69],"we":[70,94,141],"take":[71],"advantage":[72],"nonstationarity":[75],"way":[80],"that":[81],"similar":[83],"psychoacoustics":[86],"precedence":[89],"effect.":[90],"separation,":[93,140],"use":[95,125],"same":[97],"part":[101],"simple":[104],"probabilistic":[105],"generative":[106],"model":[107,116,120,128],"cues.":[110],"We":[111],"combine":[112],"with":[117],"mixture":[119],"log-spectra":[123],"combined":[127],"do":[130],"separation.":[133],"both":[135,150],"show":[142],"significant":[143],"performance":[144],"improvements":[145],"over":[146],"existing":[147],"techniques":[148],"on":[149],"simulated":[153],"data":[154],"range":[157],"acoustic":[159]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2016-06-24T00:00:00"}
