{"id":"https://openalex.org/W2282641350","doi":"https://doi.org/10.21437/interspeech.2015-360","title":"Using audio and visual information for single channel speaker separation","display_name":"Using audio and visual information for single channel speaker separation","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2282641350","doi":"https://doi.org/10.21437/interspeech.2015-360","mag":"2282641350"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-360","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ueaeprints.uea.ac.uk/id/eprint/55880/1/interspeech2015_ss_v3.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101472029","display_name":"Faheem Khan","orcid":"https://orcid.org/0000-0003-2098-4134"},"institutions":[{"id":"https://openalex.org/I4210154218","display_name":"University of Science and Technology Bannu","ror":"https://ror.org/04be2dn15","country_code":"PK","type":"education","lineage":["https://openalex.org/I4210154218"]},{"id":"https://openalex.org/I1118541","display_name":"University of East Anglia","ror":"https://ror.org/026k5mg93","country_code":"GB","type":"education","lineage":["https://openalex.org/I1118541"]}],"countries":["GB","PK"],"is_corresponding":true,"raw_author_name":"Faheem Khan","raw_affiliation_strings":["Department of Software Engineering, University of Science and Technology, Bannu, Pakistan","School of Computing Sciences, University of East Anglia, Norwich, UK"],"affiliations":[{"raw_affiliation_string":"Department of Software Engineering, University of Science and Technology, Bannu, Pakistan","institution_ids":["https://openalex.org/I4210154218"]},{"raw_affiliation_string":"School of Computing Sciences, University of East Anglia, Norwich, UK","institution_ids":["https://openalex.org/I1118541"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023076395","display_name":"Ben Milner","orcid":null},"institutions":[{"id":"https://openalex.org/I1118541","display_name":"University of East Anglia","ror":"https://ror.org/026k5mg93","country_code":"GB","type":"education","lineage":["https://openalex.org/I1118541"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ben Milner","raw_affiliation_strings":["School of Computing Sciences, University of East Anglia, Norwich, UK"],"affiliations":[{"raw_affiliation_string":"School of Computing Sciences, University of East Anglia, Norwich, UK","institution_ids":["https://openalex.org/I1118541"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101472029"],"corresponding_institution_ids":["https://openalex.org/I1118541","https://openalex.org/I4210154218"],"apc_list":null,"apc_paid":null,"fwci":0.5788,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.69525013,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1517","last_page":"1521"},"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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":0.9983999729156494,"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":0.817640483379364},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7580417394638062},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.627031683921814},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5999031662940979},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5409390330314636},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5289523601531982},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4939742684364319},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48264914751052856},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45709624886512756},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38507404923439026},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.1369156539440155}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.817640483379364},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7580417394638062},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.627031683921814},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5999031662940979},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5409390330314636},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5289523601531982},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4939742684364319},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48264914751052856},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45709624886512756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38507404923439026},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1369156539440155},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2015-360","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},{"id":"pmh:oai:ueaeprints.uea.ac.uk:55880","is_oa":true,"landing_page_url":null,"pdf_url":"https://ueaeprints.uea.ac.uk/id/eprint/55880/1/interspeech2015_ss_v3.pdf","source":{"id":"https://openalex.org/S4306400384","display_name":"UEA Digital Repository (University of East Anglia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1118541","host_organization_name":"University of East Anglia","host_organization_lineage":["https://openalex.org/I1118541"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":{"id":"pmh:oai:ueaeprints.uea.ac.uk:55880","is_oa":true,"landing_page_url":null,"pdf_url":"https://ueaeprints.uea.ac.uk/id/eprint/55880/1/interspeech2015_ss_v3.pdf","source":{"id":"https://openalex.org/S4306400384","display_name":"UEA Digital Repository (University of East Anglia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1118541","host_organization_name":"University of East Anglia","host_organization_lineage":["https://openalex.org/I1118541"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2282641350.pdf","grobid_xml":"https://content.openalex.org/works/W2282641350.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W44831635","https://openalex.org/W76597279","https://openalex.org/W1588594383","https://openalex.org/W2015143272","https://openalex.org/W2018651852","https://openalex.org/W2034040413","https://openalex.org/W2070707809","https://openalex.org/W2099128937","https://openalex.org/W2103135337","https://openalex.org/W2111070087","https://openalex.org/W2115560299","https://openalex.org/W2119901478","https://openalex.org/W2127211243","https://openalex.org/W2127851351","https://openalex.org/W2147455188","https://openalex.org/W2167667216","https://openalex.org/W2172803778","https://openalex.org/W2397008871","https://openalex.org/W2399672261","https://openalex.org/W2407692257","https://openalex.org/W2561557072","https://openalex.org/W3143833948"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"This":[0,88],"work":[1,27],"proposes":[2],"a":[3,16,20,65,77],"method":[4,35],"to":[5,14,48,53,95],"exploit":[6],"both":[7,131],"audio":[8,100],"and":[9,44,68,126,134],"vi-":[10],"sual":[11],"speech":[12,51,101,105,132,135],"information":[13,52],"extract":[15],"target":[17],"speaker":[18,37,108,122],"from":[19,64,85,106],"mix-":[21,71],"ture":[22,72],"of":[23,36,73,80,91],"competing":[24],"speakers.":[25],"The":[26,58],"begins":[28],"by":[29],"taking":[30],"an":[31],"ef-":[32],"fective":[33],"audio-only":[34,125],"separation,":[38],"namely":[39],"the":[40,55,70,92,99,110,119],"soft":[41],"mask":[42],"method,":[43],"modifying":[45],"its":[46],"operation":[47],"allow":[49],"visual":[50,81,104],"improve":[54],"separation":[56,93,123],"process.":[57],"au-":[59],"dio":[60],"input":[61],"is":[62],"taken":[63],"single":[66],"channel":[67],"includes":[69],"speakers,":[74],"where":[75],"as":[76],"separate":[78],"set":[79],"features":[82],"are":[83,115],"extracted":[84],"each":[86,107],"speaker.":[87],"allows":[89],"modification":[90],"process":[94],"include":[96],"not":[97],"only":[98],"but":[102],"also":[103],"in":[109],"mixture.":[111],"Experimen-":[112],"tal":[113],"results":[114],"presented":[116],"that":[117],"compare":[118],"proposed":[120],"audio-visual":[121],"with":[124],"visual-only":[127],"methods":[128],"us-":[129],"ing":[130],"quality":[133],"intelligibility":[136],"metrics.":[137]},"counts_by_year":[{"year":2018,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}