{"id":"https://openalex.org/W2115087482","doi":"https://doi.org/10.1109/ssp.2012.6319789","title":"Reverberant speech separation based on audio-visual dictionary learning and binaural cues","display_name":"Reverberant speech separation based on audio-visual dictionary learning and binaural cues","publication_year":2012,"publication_date":"2012-08-01","ids":{"openalex":"https://openalex.org/W2115087482","doi":"https://doi.org/10.1109/ssp.2012.6319789","mag":"2115087482"},"language":"en","primary_location":{"id":"doi:10.1109/ssp.2012.6319789","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssp.2012.6319789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Statistical Signal Processing Workshop (SSP)","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/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"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, 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"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, 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 Jackson","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","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"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5074138677"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":0.4955,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68658791,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"664","last_page":"667"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9995999932289124,"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":0.9986000061035156,"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/binaural-recording","display_name":"Binaural recording","score":0.8265066146850586},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7454562783241272},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6738759279251099},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5982670187950134},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5712607502937317},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.454262912273407},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3941328823566437},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32516324520111084},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11190322041511536}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.8265066146850586},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7454562783241272},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6738759279251099},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5982670187950134},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5712607502937317},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.454262912273407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3941328823566437},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32516324520111084},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11190322041511536},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/ssp.2012.6319789","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssp.2012.6319789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Statistical Signal Processing Workshop (SSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:alma.44SUR_INST:11138428370002346","is_oa":false,"landing_page_url":null,"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.728.563","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.728.563","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/LiuWJB_SSP_2012.pdf","raw_type":"text"},{"id":"pmh:oai:eprints.kingston.ac.uk:43483","is_oa":false,"landing_page_url":"http://eprints.kingston.ac.uk/id/eprint/43483/","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":"Conference or Workshop Item"},{"id":"pmh:oai:epubs.surrey.ac.uk:771638","is_oa":false,"landing_page_url":"http://epubs.surrey.ac.uk/771638/1/LiuWangJacksonBarnard_SSP12_preprint.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":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4699999988079071,"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1527240141","https://openalex.org/W1787078711","https://openalex.org/W2129171989","https://openalex.org/W2132877328","https://openalex.org/W2135081730","https://openalex.org/W2136682440","https://openalex.org/W2142352693","https://openalex.org/W2151693816","https://openalex.org/W2169491631","https://openalex.org/W6631618440"],"related_works":["https://openalex.org/W2766995619","https://openalex.org/W4224270619","https://openalex.org/W2579722767","https://openalex.org/W2168148781","https://openalex.org/W2026165661","https://openalex.org/W1991848873","https://openalex.org/W2783525307","https://openalex.org/W2593008828","https://openalex.org/W2099651033","https://openalex.org/W2155323221"],"abstract_inverted_index":{"Probabilistic":[0],"models":[1,38],"of":[2,34],"binaural":[3,35,117],"cues,":[4],"such":[5],"as":[6],"the":[7,13,23,27,48,55,76,90,95,102,116,127],"interaural":[8,14],"phase":[9],"difference":[10,16],"(IPD)":[11],"and":[12,99,130],"level":[15],"(ILD),":[17],"can":[18],"be":[19],"used":[20],"to":[21,105,115],"obtain":[22,106],"audio":[24,57,103],"mask":[25,86,104],"in":[26],"time-frequency":[28],"(TF)":[29],"domain,":[30],"for":[31,74,119,135],"source":[32,120],"separation":[33],"mixtures.":[36],"Those":[37],"are,":[39],"however,":[40],"often":[41],"degraded":[42],"by":[43,63],"acoustic":[44,64],"noise.":[45,65],"In":[46,66],"contrast,":[47],"video":[49,91],"stream":[50,58],"contains":[51],"relevant":[52],"information":[53],"about":[54],"synchronous":[56],"that":[59],"is":[60,87,112],"not":[61],"affected":[62],"this":[67],"paper,":[68],"we":[69],"present":[70],"a":[71,107],"novel":[72],"method":[73],"modeling":[75],"audio-visual":[77,109],"(AV)":[78],"coherence":[79],"based":[80,93],"on":[81,94,126],"dictionary":[82],"learning.":[83],"A":[84],"visual":[85],"constructed":[88],"from":[89],"signal":[92,118],"learnt":[96],"AV":[97],"dictionary,":[98],"incorporated":[100],"with":[101],"noise-robust":[108],"mask,":[110],"which":[111],"then":[113],"applied":[114],"separation.":[121],"We":[122],"tested":[123],"our":[124],"algorithm":[125],"XM2VTS":[128],"database,":[129],"observed":[131],"considerable":[132],"performance":[133],"improvement":[134],"noise":[136],"corrupted":[137],"signals.":[138]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
