{"id":"https://openalex.org/W2804093409","doi":"https://doi.org/10.1109/taslp.2018.2835719","title":"Using Visual Speech Information in Masking Methods for Audio Speaker Separation","display_name":"Using Visual Speech Information in Masking Methods for Audio Speaker Separation","publication_year":2018,"publication_date":"2018-05-18","ids":{"openalex":"https://openalex.org/W2804093409","doi":"https://doi.org/10.1109/taslp.2018.2835719","mag":"2804093409"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2835719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2835719","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language 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/A5101472029","display_name":"Faheem Khan","orcid":"https://orcid.org/0000-0003-2098-4134"},"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":true,"raw_author_name":"Faheem Ullah Khan","raw_affiliation_strings":["School of Computing Sciences, University of East Anglia, Norwich, Norfolk, U.K"],"affiliations":[{"raw_affiliation_string":"School of Computing Sciences, University of East Anglia, Norwich, Norfolk, U.K","institution_ids":["https://openalex.org/I1118541"]}]},{"author_position":"middle","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 P. Milner","raw_affiliation_strings":["School of Computing Sciences, University of East Anglia, Norwich, Norfolk, U.K"],"affiliations":[{"raw_affiliation_string":"School of Computing Sciences, University of East Anglia, Norwich, Norfolk, U.K","institution_ids":["https://openalex.org/I1118541"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022796258","display_name":"Thomas Le Cornu","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":"Thomas Le Cornu","raw_affiliation_strings":["School of Computing Sciences, University of East Anglia, Norwich, Norfolk, U.K"],"affiliations":[{"raw_affiliation_string":"School of Computing Sciences, University of East Anglia, Norwich, Norfolk, U.K","institution_ids":["https://openalex.org/I1118541"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101472029"],"corresponding_institution_ids":["https://openalex.org/I1118541"],"apc_list":null,"apc_paid":null,"fwci":1.156,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.78890141,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"26","issue":"10","first_page":"1742","last_page":"1754"},"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":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/speech-recognition","display_name":"Speech recognition","score":0.7257659435272217},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.712475061416626},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7102830410003662},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6310919523239136},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.467099130153656},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.11066415905952454},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.043001413345336914},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.040601372718811035}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7257659435272217},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.712475061416626},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7102830410003662},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6310919523239136},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.467099130153656},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.11066415905952454},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.043001413345336914},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.040601372718811035},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2018.2835719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2835719","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:ueaeprints.uea.ac.uk:67404","is_oa":false,"landing_page_url":null,"pdf_url":null,"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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W44831635","https://openalex.org/W142803501","https://openalex.org/W1554064406","https://openalex.org/W1790748249","https://openalex.org/W1908325895","https://openalex.org/W1963970749","https://openalex.org/W1970924839","https://openalex.org/W1979099822","https://openalex.org/W2015143272","https://openalex.org/W2017608047","https://openalex.org/W2018840451","https://openalex.org/W2032618685","https://openalex.org/W2038010270","https://openalex.org/W2067295501","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2085191029","https://openalex.org/W2097998348","https://openalex.org/W2099128937","https://openalex.org/W2099940393","https://openalex.org/W2103135337","https://openalex.org/W2104263160","https://openalex.org/W2111070087","https://openalex.org/W2112739286","https://openalex.org/W2114824844","https://openalex.org/W2116529913","https://openalex.org/W2119901478","https://openalex.org/W2120535071","https://openalex.org/W2122663884","https://openalex.org/W2122982914","https://openalex.org/W2127025755","https://openalex.org/W2127211243","https://openalex.org/W2127851351","https://openalex.org/W2134383396","https://openalex.org/W2137400100","https://openalex.org/W2149425615","https://openalex.org/W2152826865","https://openalex.org/W2157867825","https://openalex.org/W2167734090","https://openalex.org/W2168379380","https://openalex.org/W2169896329","https://openalex.org/W2282641350","https://openalex.org/W2293856338","https://openalex.org/W2304609584","https://openalex.org/W2338740482","https://openalex.org/W2397008871","https://openalex.org/W2421316443","https://openalex.org/W2482792214","https://openalex.org/W2539331707","https://openalex.org/W2561557072","https://openalex.org/W2577762507","https://openalex.org/W2625027024","https://openalex.org/W2895674046","https://openalex.org/W2962866211","https://openalex.org/W3124794156","https://openalex.org/W4285719527","https://openalex.org/W6601817925","https://openalex.org/W6605737493","https://openalex.org/W6632994029","https://openalex.org/W6639968709","https://openalex.org/W6674385629","https://openalex.org/W6675117242","https://openalex.org/W6684878041","https://openalex.org/W6695671974","https://openalex.org/W6712456248","https://openalex.org/W6717465090","https://openalex.org/W6743462201"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2271369634","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W4245955731","https://openalex.org/W2393726419","https://openalex.org/W2380912101","https://openalex.org/W1984634519"],"abstract_inverted_index":{"This":[0],"paper":[1],"examines":[2],"whether":[3],"visual":[4,47,93,152],"speech":[5,48,73,94,135],"information":[6,95,153],"can":[7],"be":[8],"effective":[9],"within":[10],"audio-masking-based":[11],"speaker":[12,33,86,118],"separation":[13,34,87,119],"to":[14,44,50,71,91,96,125,154],"improve":[15],"the":[16,21,46,72,110,133,138,156],"quality":[17,102],"and":[18,62,103,113,140,151],"intelligibility":[19,104],"of":[20,27,117],"target":[22,134],"speech.":[23],"Two":[24],"visual-only":[25,139],"methods":[26,116],"generating":[28],"an":[29,51,76],"audio":[30,52,77,150],"mask":[31],"for":[32,85],"are":[35,67,106],"first":[36],"developed.":[37],"These":[38,128],"use":[39],"a":[40,82],"deep":[41],"neural":[42],"network":[43],"map":[45],"features":[49],"feature":[53],"space":[54],"from":[55,123],"which":[56,88],"both":[57],"visually":[58,63],"derived":[59,64],"binary":[60],"masks":[61,66],"ratio":[65,78,99],"estimated,":[68],"before":[69],"application":[70],"mixture.":[74],"Second,":[75],"masking":[79,115],"method":[80],"forms":[81],"baseline":[83],"approach":[84],"is":[89],"extended":[90],"exploit":[92],"form":[97],"audio-visual":[98,114,157],"masks.":[100,158],"Speech":[101],"tests":[105],"carried":[107],"out":[108],"on":[109],"visual-only,":[111],"audio-only,":[112],"at":[120],"mixing":[121],"levels":[122],"-10":[124],"+10":[126],"dB.":[127],"reveal":[129],"substantial":[130],"improvements":[131],"in":[132],"when":[136,148],"applying":[137],"audio-only":[141],"masks,":[142],"but":[143],"with":[144],"highest":[145],"performance":[146],"occurring":[147],"combining":[149],"create":[155]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}