{"id":"https://openalex.org/W2886232760","doi":"https://doi.org/10.21437/interspeech.2018-2516","title":"DNN Driven Speaker Independent Audio-Visual Mask Estimation for Speech Separation","display_name":"DNN Driven Speaker Independent Audio-Visual Mask Estimation for Speech Separation","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2886232760","doi":"https://doi.org/10.21437/interspeech.2018-2516","mag":"2886232760"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-2516","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1808.00060","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068981769","display_name":"Mandar Gogate","orcid":"https://orcid.org/0000-0003-1712-9014"},"institutions":[{"id":"https://openalex.org/I12093191","display_name":"University of Stirling","ror":"https://ror.org/045wgfr59","country_code":"GB","type":"education","lineage":["https://openalex.org/I12093191"]},{"id":"https://openalex.org/I74796645","display_name":"Birla Institute of Technology and Science, Pilani","ror":"https://ror.org/001p3jz28","country_code":"IN","type":"education","lineage":["https://openalex.org/I74796645"]}],"countries":["GB","IN"],"is_corresponding":false,"raw_author_name":"Mandar Gogate","raw_affiliation_strings":["University of Stirling (Stirling FK9 4LA - Royaume-Uni)","BITS Pilani - Birla Institute of Technology and Science (idya Vihar , Pilani 333031, Rajasthan, India  - Inde)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Stirling (Stirling FK9 4LA - Royaume-Uni)","institution_ids":["https://openalex.org/I12093191"]},{"raw_affiliation_string":"BITS Pilani - Birla Institute of Technology and Science (idya Vihar , Pilani 333031, Rajasthan, India  - Inde)","institution_ids":["https://openalex.org/I74796645"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082626629","display_name":"Ahsan Adeel","orcid":"https://orcid.org/0000-0001-9153-6756"},"institutions":[{"id":"https://openalex.org/I12093191","display_name":"University of Stirling","ror":"https://ror.org/045wgfr59","country_code":"GB","type":"education","lineage":["https://openalex.org/I12093191"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ahsan Adeel","raw_affiliation_strings":["University of Stirling (Stirling FK9 4LA - Royaume-Uni)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Stirling (Stirling FK9 4LA - Royaume-Uni)","institution_ids":["https://openalex.org/I12093191"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013266148","display_name":"Ricard Marxer","orcid":"https://orcid.org/0000-0001-5099-5059"},"institutions":[{"id":"https://openalex.org/I21491767","display_name":"Aix-Marseille Universit\u00e9","ror":"https://ror.org/035xkbk20","country_code":"FR","type":"education","lineage":["https://openalex.org/I21491767"]},{"id":"https://openalex.org/I4210114274","display_name":"Laboratoire d\u2019Informatique et Syst\u00e8mes","ror":"https://ror.org/0257sgk90","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I143002897","https://openalex.org/I21491767","https://openalex.org/I4210114274"]},{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["FR","GB"],"is_corresponding":false,"raw_author_name":"Ricard Marxer","raw_affiliation_strings":["DYNI - DYNamiques de l\u2019Information (France)","LIS - Laboratoire d'Informatique et Syst\u00e8mes (Aix Marseille Universit\u00e9 \u2013 Campus de Saint J\u00e9r\u00f4me \u2013 Bat. Polytech, 52 Av. Escadrille Normandie Niemen, 13397 Marseille Cedex 20 - France)","University of Sheffield [Sheffield] (Western Bank Sheffield S10 2TN - Royaume-Uni)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DYNI - DYNamiques de l\u2019Information (France)","institution_ids":[]},{"raw_affiliation_string":"LIS - Laboratoire d'Informatique et Syst\u00e8mes (Aix Marseille Universit\u00e9 \u2013 Campus de Saint J\u00e9r\u00f4me \u2013 Bat. Polytech, 52 Av. Escadrille Normandie Niemen, 13397 Marseille Cedex 20 - France)","institution_ids":["https://openalex.org/I4210114274","https://openalex.org/I21491767"]},{"raw_affiliation_string":"University of Sheffield [Sheffield] (Western Bank Sheffield S10 2TN - Royaume-Uni)","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074458312","display_name":"Jon Barker","orcid":"https://orcid.org/0000-0002-1684-5660"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jon Barker","raw_affiliation_strings":["Department of Computer Sciences [Scheffield] (The Department of Computer Science University of Scheffield Regent Court 211 Portobello Sheffield, S1 4DP. UNITED KINGDOM. Tel: +44 (0) 114 222 1800 Fax: +44 (0) 114 222 1810 - Royaume-Uni)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences [Scheffield] (The Department of Computer Science University of Scheffield Regent Court 211 Portobello Sheffield, S1 4DP. UNITED KINGDOM. Tel: +44 (0) 114 222 1800 Fax: +44 (0) 114 222 1810 - Royaume-Uni)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062211930","display_name":"Amir Hussain","orcid":"https://orcid.org/0000-0002-8080-082X"},"institutions":[{"id":"https://openalex.org/I12093191","display_name":"University of Stirling","ror":"https://ror.org/045wgfr59","country_code":"GB","type":"education","lineage":["https://openalex.org/I12093191"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Amir Hussain","raw_affiliation_strings":["University of Stirling (Stirling FK9 4LA - Royaume-Uni)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Stirling (Stirling FK9 4LA - Royaume-Uni)","institution_ids":["https://openalex.org/I12093191"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2723","last_page":"2727"},"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":0.9990000128746033,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.998199999332428,"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":0.8406780362129211},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7361112833023071},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.54152911901474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48824360966682434},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.4707670211791992},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4706292152404785},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4167303442955017},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3437400460243225},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12482234835624695}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8406780362129211},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7361112833023071},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.54152911901474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48824360966682434},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.4707670211791992},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4706292152404785},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4167303442955017},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3437400460243225},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12482234835624695},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2018-2516","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1808.00060","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.00060","pdf_url":"https://arxiv.org/pdf/1808.00060","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:HAL:hal-01868604v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01868604","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://interspeech2018.org/","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:dspace.stir.ac.uk:1893/28200","is_oa":false,"landing_page_url":"http://hdl.handle.net/1893/28200","pdf_url":null,"source":{"id":"https://openalex.org/S4306400268","display_name":"Stirling Online Research Repository (University of Stirling)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I12093191","host_organization_name":"University of Stirling","host_organization_lineage":["https://openalex.org/I12093191"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"pmh:oai:napier-surface.worktribe.com:1792250","is_oa":false,"landing_page_url":"http://researchrepository.napier.ac.uk/Output/1792250","pdf_url":null,"source":{"id":"https://openalex.org/S4306400544","display_name":"Research Output (Edinburgh Napier University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I251738","host_organization_name":"Edinburgh Napier University","host_organization_lineage":["https://openalex.org/I251738"],"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 Proceeding"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1808.00060","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1808.00060","pdf_url":"https://arxiv.org/pdf/1808.00060","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G4769349813","display_name":null,"funder_award_id":"EP/M026981/1","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":22,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2003203076","https://openalex.org/W2012910847","https://openalex.org/W2015143272","https://openalex.org/W2018651852","https://openalex.org/W2027701650","https://openalex.org/W2035576074","https://openalex.org/W2043216213","https://openalex.org/W2055516313","https://openalex.org/W2139047213","https://openalex.org/W2141411743","https://openalex.org/W2164598857","https://openalex.org/W2289394825","https://openalex.org/W2364134690","https://openalex.org/W2397260994","https://openalex.org/W2398042854","https://openalex.org/W2678916739","https://openalex.org/W2746601360","https://openalex.org/W2765425905","https://openalex.org/W2787592166","https://openalex.org/W2790760353","https://openalex.org/W2964121744"],"related_works":["https://openalex.org/W2012531322","https://openalex.org/W2785900585","https://openalex.org/W2353730437","https://openalex.org/W2490303674","https://openalex.org/W2609066826","https://openalex.org/W2810752900","https://openalex.org/W2365677836","https://openalex.org/W2531295127","https://openalex.org/W2127461790","https://openalex.org/W2069324367"],"abstract_inverted_index":{"Human":[0],"auditory":[1],"cortex":[2],"excels":[3],"at":[4],"selectively":[5],"suppressing":[6],"background":[7],"noise":[8],"to":[9,25,34,104,145],"focus":[10,36],"on":[11,37],"a":[12,50,98,110],"target":[13,38],"speaker.":[14],"The":[15,62,121],"process":[16],"of":[17,73,109,127,136],"selective":[18],"attention":[19],"in":[20,125],"the":[21,28,70,106],"brain":[22],"is":[23,102],"known":[24],"contextually":[26,68],"exploit":[27],"available":[29],"audio":[30,75],"and":[31,76,84,92,117,130,147,156],"visual":[32,78],"cues":[33],"better":[35],"speaker":[39,154],"while":[40],"filtering":[41],"out":[42],"other":[43],"noises.":[44],"In":[45],"this":[46],"study,":[47],"we":[48],"propose":[49],"novel":[51],"deep":[52],"neural":[53],"network":[54],"(DNN)":[55],"based":[56],"audiovisual":[57],"(AV)":[58],"mask":[59,65,82,95,140,149],"estimation":[60,66,83,141,150],"model.":[61],"proposed":[63,138],"AV":[64,89,139],"model":[67,142],"integrates":[69],"temporal":[71],"dynamics":[72],"both":[74,153],"noise-immune":[77],"features":[79,90],"for":[80,152],"improved":[81],"speech":[85,128],"separation.":[86],"For":[87],"optimal":[88],"extraction":[91],"ideal":[93],"binary":[94],"(IBM)":[96],"estimation,":[97],"hybrid":[99],"DNN":[100],"architecture":[101],"exploited":[103],"leverages":[105],"complementary":[107],"strengths":[108],"stacked":[111],"long":[112],"short":[113],"term":[114],"memory":[115],"(LSTM)":[116],"convolution":[118],"LSTM":[119],"network.":[120],"comparative":[122],"simulation":[123],"results":[124],"terms":[126],"quality":[129],"intelligibility":[131],"demonstrate":[132],"significant":[133],"performance":[134],"improvement":[135],"our":[137],"as":[143],"compared":[144],"audio-only":[146],"visual-only":[148],"approaches":[151],"dependent":[155],"independent":[157],"scenarios.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2018-08-22T00:00:00"}
