{"id":"https://openalex.org/W1986572644","doi":"https://doi.org/10.1109/icdsp.2013.6622780","title":"Two-stage audio-visual speech dereverberation and separation based on models of the interaural spatial cues and spatial covariance","display_name":"Two-stage audio-visual speech dereverberation and separation based on models of the interaural spatial cues and spatial covariance","publication_year":2013,"publication_date":"2013-07-01","ids":{"openalex":"https://openalex.org/W1986572644","doi":"https://doi.org/10.1109/icdsp.2013.6622780","mag":"1986572644"},"language":"en","primary_location":{"id":"doi:10.1109/icdsp.2013.6622780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdsp.2013.6622780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 18th International Conference on Digital Signal Processing (DSP)","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/A5038491744","display_name":"Muhammad Salman Khan","orcid":"https://orcid.org/0000-0001-9709-8179"},"institutions":[{"id":"https://openalex.org/I143804889","display_name":"Loughborough University","ror":"https://ror.org/04vg4w365","country_code":"GB","type":"education","lineage":["https://openalex.org/I143804889"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Muhammad Salman Khan","raw_affiliation_strings":["Advanced Signal Processing Group, School of Electronic, Electrical and Systems Engineering,, Loughborough University, Leicestershire, UK","Adv. Signal Process. Group, Loughborough Univ., Loughborough, UK"],"affiliations":[{"raw_affiliation_string":"Advanced Signal Processing Group, School of Electronic, Electrical and Systems Engineering,, Loughborough University, Leicestershire, UK","institution_ids":["https://openalex.org/I143804889"]},{"raw_affiliation_string":"Adv. Signal Process. Group, Loughborough Univ., Loughborough, UK","institution_ids":["https://openalex.org/I143804889"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053121936","display_name":"Syed Mohsen Naqvi","orcid":"https://orcid.org/0000-0002-1547-0908"},"institutions":[{"id":"https://openalex.org/I143804889","display_name":"Loughborough University","ror":"https://ror.org/04vg4w365","country_code":"GB","type":"education","lineage":["https://openalex.org/I143804889"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Syed Mohsen Naqvi","raw_affiliation_strings":["Advanced Signal Processing Group, School of Electronic, Electrical and Systems Engineering,, Loughborough University, Leicestershire, UK","Adv. Signal Process. Group, Loughborough Univ., Loughborough, UK"],"affiliations":[{"raw_affiliation_string":"Advanced Signal Processing Group, School of Electronic, Electrical and Systems Engineering,, Loughborough University, Leicestershire, UK","institution_ids":["https://openalex.org/I143804889"]},{"raw_affiliation_string":"Adv. Signal Process. Group, Loughborough Univ., Loughborough, UK","institution_ids":["https://openalex.org/I143804889"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007993661","display_name":"Jonathon A. Chambers","orcid":"https://orcid.org/0000-0002-7224-8553"},"institutions":[{"id":"https://openalex.org/I143804889","display_name":"Loughborough University","ror":"https://ror.org/04vg4w365","country_code":"GB","type":"education","lineage":["https://openalex.org/I143804889"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jonathon Chambers","raw_affiliation_strings":["Advanced Signal Processing Group, School of Electronic, Electrical and Systems Engineering,, Loughborough University, Leicestershire, UK","Adv. Signal Process. Group, Loughborough Univ., Loughborough, UK"],"affiliations":[{"raw_affiliation_string":"Advanced Signal Processing Group, School of Electronic, Electrical and Systems Engineering,, Loughborough University, Leicestershire, UK","institution_ids":["https://openalex.org/I143804889"]},{"raw_affiliation_string":"Adv. Signal Process. Group, Loughborough Univ., Loughborough, UK","institution_ids":["https://openalex.org/I143804889"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5038491744"],"corresponding_institution_ids":["https://openalex.org/I143804889"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.06249268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"87","issue":null,"first_page":"1","last_page":"6"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9983999729156494,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9972000122070312,"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/pesq","display_name":"PESQ","score":0.802375078201294},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6958914995193481},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6940244436264038},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.6181469559669495},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.5855485796928406},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5482174158096313},{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.5304868817329407},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5158252120018005},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.48699647188186646},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4193421006202698},{"id":"https://openalex.org/keywords/interaural-time-difference","display_name":"Interaural time difference","score":0.41432714462280273},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40267467498779297},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3772612512111664},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.35508406162261963},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21756228804588318},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.18333259224891663},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.12553563714027405},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08492740988731384}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.802375078201294},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6958914995193481},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6940244436264038},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.6181469559669495},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.5855485796928406},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5482174158096313},{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.5304868817329407},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5158252120018005},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.48699647188186646},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4193421006202698},{"id":"https://openalex.org/C103364767","wikidata":"https://www.wikidata.org/wiki/Q1807562","display_name":"Interaural time difference","level":3,"score":0.41432714462280273},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40267467498779297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3772612512111664},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.35508406162261963},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21756228804588318},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.18333259224891663},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.12553563714027405},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08492740988731384},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","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/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdsp.2013.6622780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdsp.2013.6622780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 18th International Conference on Digital Signal Processing (DSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5799999833106995,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1987906574","https://openalex.org/W1989919048","https://openalex.org/W2014621385","https://openalex.org/W2015394094","https://openalex.org/W2016157229","https://openalex.org/W2034040413","https://openalex.org/W2043532615","https://openalex.org/W2095901148","https://openalex.org/W2096301647","https://openalex.org/W2098382639","https://openalex.org/W2110120390","https://openalex.org/W2117008429","https://openalex.org/W2117678320","https://openalex.org/W2122171611","https://openalex.org/W2122884709","https://openalex.org/W2124535811","https://openalex.org/W2127851351","https://openalex.org/W2129171989","https://openalex.org/W2135081730","https://openalex.org/W2142352693","https://openalex.org/W2143027228","https://openalex.org/W2144404214","https://openalex.org/W2146053319","https://openalex.org/W2168010845","https://openalex.org/W2188162373","https://openalex.org/W3127686677","https://openalex.org/W6654226266","https://openalex.org/W6661161230","https://openalex.org/W6677609933","https://openalex.org/W6686978693"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W3016109656","https://openalex.org/W3135613579","https://openalex.org/W1973895194","https://openalex.org/W2166831097","https://openalex.org/W4386746628","https://openalex.org/W4388016426","https://openalex.org/W2546593254","https://openalex.org/W1980687383","https://openalex.org/W3209446892"],"abstract_inverted_index":{"This":[0],"work":[1],"presents":[2],"a":[3,44,153],"two-stage":[4],"speech":[5,39,125,141],"source":[6,105,157],"separation":[7,158],"algorithm":[8,114],"based":[9],"on":[10],"combined":[11],"models":[12,97],"of":[13,22,25,94,131,140],"interaural":[14,62,67],"cues":[15],"and":[16,65,70,98,136],"spatial":[17,59,72],"covariance":[18,73],"which":[19],"utilize":[20],"knowledge":[21],"the":[23,26,32,36,50,54,57,61,66,71,77,99,109,123,132,137,146],"locations":[24],"sources":[27],"estimated":[28],"through":[29],"video.":[30],"In":[31,53],"first":[33],"pre-processing":[34,151],"stage":[35],"late":[37],"reverberant":[38,161],"components":[40],"are":[41,74,106,119],"suppressed":[42],"by":[43],"spectral":[45],"subtraction":[46],"rule":[47],"to":[48,83,89,103,121],"dereverberate":[49],"observed":[51],"mixture.":[52],"second":[55],"stage,":[56],"binaural":[58],"parameters,":[60],"phase":[63],"difference":[64],"level":[68],"difference,":[69],"modeled":[75],"in":[76,129,159],"short-time":[78],"Fourier":[79],"transform":[80],"(STFT)":[81],"domain":[82],"classify":[84],"individual":[85,124],"time-frequency":[86],"(TF)":[87],"units":[88],"each":[90,104],"source.":[91],"The":[92,113],"parameters":[93],"these":[95],"probabilistic":[96],"TF":[100,116],"regions":[101],"assigned":[102],"updated":[107],"with":[108,150],"expectation-maximization":[110],"(EM)":[111],"algorithm.":[112],"generates":[115],"masks":[117],"that":[118,145],"used":[120],"reconstruct":[122],"sources.":[126],"Objective":[127],"results,":[128],"terms":[130],"signal-to-distortion":[133],"ratio":[134],"(SDR)":[135],"perceptual":[138],"evaluation":[139],"quality":[142],"(PESQ),":[143],"confirm":[144],"proposed":[147],"multimodal":[148],"method":[149],"is":[152],"promising":[154],"approach":[155],"for":[156],"highly":[160],"rooms.":[162]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
