{"id":"https://openalex.org/W2018840451","doi":"https://doi.org/10.1109/tsp.2013.2277834","title":"Source Separation of Convolutive and Noisy Mixtures Using Audio-Visual Dictionary Learning and Probabilistic Time-Frequency Masking","display_name":"Source Separation of Convolutive and Noisy Mixtures Using Audio-Visual Dictionary Learning and Probabilistic Time-Frequency Masking","publication_year":2013,"publication_date":"2013-08-08","ids":{"openalex":"https://openalex.org/W2018840451","doi":"https://doi.org/10.1109/tsp.2013.2277834","mag":"2018840451"},"language":"en","primary_location":{"id":"doi:10.1109/tsp.2013.2277834","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp.2013.2277834","pdf_url":null,"source":{"id":"https://openalex.org/S168680287","display_name":"IEEE Transactions on Signal Processing","issn_l":"1053-587X","issn":["1053-587X","1941-0476"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Signal Processing","raw_type":"journal-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/A5074138677","display_name":"Qingju Liu","orcid":"https://orcid.org/0000-0003-2288-3417"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Qingju Liu","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, UK","Centre for Vision Speech & Signal Process., Univ. of Surrey, Guildford, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision Speech & Signal Process., Univ. of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, UK","Centre for Vision Speech & Signal Process., Univ. of Surrey, Guildford, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision Speech & Signal Process., Univ. of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022165330","display_name":"Philip J. B. Jackson","orcid":"https://orcid.org/0000-0001-7933-5935"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philip J. B. Jackson","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, UK","Centre for Vision Speech & Signal Process., Univ. of Surrey, Guildford, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision Speech & Signal Process., Univ. of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027243174","display_name":"Mark Barnard","orcid":null},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark Barnard","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, UK","Centre for Vision Speech & Signal Process., Univ. of Surrey, Guildford, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision Speech & Signal Process., Univ. of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028209738","display_name":"Josef Kittler","orcid":"https://orcid.org/0000-0002-8110-9205"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Josef Kittler","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, UK","Centre for Vision Speech & Signal Process., Univ. of Surrey, Guildford, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision Speech & Signal Process., Univ. of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083892296","display_name":"Jonathon A. Chambers","orcid":"https://orcid.org/0000-0002-5820-6509"},"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":["School of Electronic, Electrical and Systems Engineering, Loughborough University, UK","Sch. of Electron., Electr. & Syst. Eng. Loughborough Univ., Loughborough, UK"],"affiliations":[{"raw_affiliation_string":"School of Electronic, Electrical and Systems Engineering, Loughborough University, UK","institution_ids":["https://openalex.org/I143804889"]},{"raw_affiliation_string":"Sch. of Electron., Electr. & Syst. Eng. Loughborough Univ., Loughborough, UK","institution_ids":["https://openalex.org/I143804889"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5074138677"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":2.8941,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.91092534,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"61","issue":"22","first_page":"5520","last_page":"5535"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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":0.9939000010490417,"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/computer-science","display_name":"Computer science","score":0.7600299119949341},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47112011909484863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4622023105621338},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.45307302474975586},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43985825777053833}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7600299119949341},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47112011909484863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4622023105621338},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.45307302474975586},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43985825777053833}],"mesh":[],"locations_count":8,"locations":[{"id":"doi:10.1109/tsp.2013.2277834","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp.2013.2277834","pdf_url":null,"source":{"id":"https://openalex.org/S168680287","display_name":"IEEE Transactions on Signal Processing","issn_l":"1053-587X","issn":["1053-587X","1941-0476"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.699.7871","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.699.7871","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://personal.ee.surrey.ac.uk/Personal/W.Wang/papers/LiuWBJKC_TSP_2013_ms.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.700.869","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.700.869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://personal.ee.surrey.ac.uk/Personal/W.Wang/papers/LiuWBJKC_TSP_2013_preprint.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.700.9013","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.700.9013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://personal.ee.surrey.ac.uk/Personal/W.Wang/papers/LiuWBJKC_TSP_2013_R1.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.703.8359","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.703.8359","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://personal.ee.surrey.ac.uk/Personal/W.Wang/papers/LiuWBJKC_TSP_2013.pdf","raw_type":"text"},{"id":"pmh:oai:alma.44SUR_INST:11138918270002346","is_oa":false,"landing_page_url":"https://openresearch.surrey.ac.uk/esploro/outputs/journalArticle/Source-separation-of-convolutive-and-noisy/99512562202346","pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:eprints.kingston.ac.uk:43477","is_oa":false,"landing_page_url":"http://eprints.kingston.ac.uk/id/eprint/43477/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400991","display_name":"Research Repository (Kingston University London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801636071","host_organization_name":"Kingston Hospital NHS Trust","host_organization_lineage":["https://openalex.org/I2801636071"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:epubs.surrey.ac.uk:801228","is_oa":false,"landing_page_url":"http://epubs.surrey.ac.uk/801228/2/SRI_deposit_agreement.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400680","display_name":"Surrey Research Insight Open Access (The University of Surrey)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28290843","host_organization_name":"University of Surrey","host_organization_lineage":["https://openalex.org/I28290843"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G7030354634","display_name":null,"funder_award_id":"EP/H050000/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8753687478","display_name":null,"funder_award_id":"EP/H012842/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W15147940","https://openalex.org/W160800111","https://openalex.org/W1548802052","https://openalex.org/W1832112969","https://openalex.org/W1956364622","https://openalex.org/W1963995223","https://openalex.org/W1986931325","https://openalex.org/W1991139021","https://openalex.org/W1996355918","https://openalex.org/W2015394094","https://openalex.org/W2016157229","https://openalex.org/W2018832332","https://openalex.org/W2027922120","https://openalex.org/W2031583051","https://openalex.org/W2074054045","https://openalex.org/W2077852110","https://openalex.org/W2084237818","https://openalex.org/W2086541583","https://openalex.org/W2096301647","https://openalex.org/W2096391593","https://openalex.org/W2099741732","https://openalex.org/W2105464873","https://openalex.org/W2105921478","https://openalex.org/W2108384452","https://openalex.org/W2109935156","https://openalex.org/W2113771288","https://openalex.org/W2113807803","https://openalex.org/W2114125447","https://openalex.org/W2115087482","https://openalex.org/W2115429828","https://openalex.org/W2117307995","https://openalex.org/W2120838354","https://openalex.org/W2124757684","https://openalex.org/W2128659236","https://openalex.org/W2129171989","https://openalex.org/W2134910060","https://openalex.org/W2135081730","https://openalex.org/W2140499889","https://openalex.org/W2140592340","https://openalex.org/W2142352693","https://openalex.org/W2142940228","https://openalex.org/W2151693816","https://openalex.org/W2154091569","https://openalex.org/W2154151281","https://openalex.org/W2155323221","https://openalex.org/W2160547390","https://openalex.org/W2161226030","https://openalex.org/W2168010845","https://openalex.org/W2169491631","https://openalex.org/W3205392798","https://openalex.org/W6640823206","https://openalex.org/W6641258197","https://openalex.org/W6671574273"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2033914206","https://openalex.org/W2042327336","https://openalex.org/W1516392727","https://openalex.org/W2171745948"],"abstract_inverted_index":{"In":[0,60],"existing":[1],"audio-visual":[2,75],"blind":[3],"source":[4],"separation":[5],"(AV-BSS)":[6],"algorithms,":[7,207],"the":[8,38,48,52,98,149,181,202,213,226],"AV":[9],"coherence":[10],"is":[11,44,190],"usually":[12],"established":[13],"through":[14],"statistical":[15],"modelling,":[16],"using":[17,195,217],"e.g.,":[18],"Gaussian":[19],"mixture":[20],"models":[21],"(GMMs).":[22],"These":[23],"methods":[24],"often":[25],"operate":[26],"in":[27,46,89],"a":[28,65,106,115,121,128,134,156,174,191],"low-dimensional":[29],"feature":[30],"space,":[31],"rendering":[32],"an":[33,160],"effective":[34],"global":[35],"representation":[36],"of":[37,51,100,168],"data.":[39],"The":[40],"local":[41,71],"information,":[42,72],"which":[43,119,189],"important":[45],"capturing":[47,69],"temporal":[49],"structure":[50],"data,":[53],"however,":[54],"has":[55],"not":[56],"been":[57],"explicitly":[58],"exploited.":[59],"this":[61],"paper,":[62],"we":[63,112,162],"propose":[64],"new":[66,116,175],"method":[67,194],"for":[68,138],"such":[70],"based":[73],"on":[74],"dictionary":[76],"learning":[77],"(AVDL).":[78],"We":[79,145,198],"address":[80],"several":[81],"challenges":[82],"associated":[83],"with":[84,185],"AVDL,":[85],"including":[86],"cross-modality":[87,142],"differences":[88],"size,":[90],"dimension":[91,131],"and":[92,102,124,130,141,172,205,208,221],"sampling":[93],"rate,":[94],"as":[95,97],"well":[96],"issues":[99],"scalability":[101],"computational":[103],"complexity.":[104],"Following":[105],"commonly":[107],"employed":[108],"bootstrap":[109],"coding-learning":[110],"process,":[111],"have":[113,199],"developed":[114],"AVDL":[117,151,183,204],"algorithm":[118,178,184],"features,":[120],"bimodality":[122],"balanced":[123],"scalable":[125],"matching":[126],"criterion,":[127],"size":[129],"adaptive":[132],"dictionary,":[133],"fast":[135],"search":[136],"index":[137],"efficient":[139],"coding,":[140],"diverse":[143],"sparsity.":[144],"also":[146],"show":[147,209],"how":[148],"proposed":[150,182,203],"can":[152],"be":[153],"incorporated":[154],"into":[155],"BSS":[157,187],"algorithm.":[158],"As":[159],"example,":[161],"consider":[163],"binaural":[164,170],"mixtures,":[165],"mimicking":[166],"aspects":[167],"human":[169],"hearing,":[171],"derive":[173],"noise-robust":[176],"AV-BSS":[177,206],"by":[179],"combining":[180],"Mandel's":[186],"method,":[188],"state-of-the-art":[192],"audio-domain":[193],"time-frequency":[196],"masking.":[197],"systematically":[200],"evaluated":[201],"their":[210],"advantages":[211],"over":[212],"corresponding":[214],"baseline":[215],"methods,":[216],"both":[218],"synthetic":[219],"data":[220,224],"visual":[222],"speech":[223],"from":[225],"multimodal":[227],"LILiR":[228],"Twotalk":[229],"corpus.":[230]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}