{"id":"https://openalex.org/W2508884455","doi":"https://doi.org/10.21437/interspeech.2016-216","title":"Combining Mask Estimates for Single Channel Audio Source Separation Using Deep Neural Networks","display_name":"Combining Mask Estimates for Single Channel Audio Source Separation Using Deep Neural Networks","publication_year":2016,"publication_date":"2016-08-29","ids":{"openalex":"https://openalex.org/W2508884455","doi":"https://doi.org/10.21437/interspeech.2016-216","mag":"2508884455"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2016-216","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-216","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","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/A5013467271","display_name":"Emad M. Grais","orcid":"https://orcid.org/0000-0002-6387-0981"},"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":"Emad M. Grais","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031121131","display_name":"Gerard Roma","orcid":"https://orcid.org/0009-0004-1287-0713"},"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":"Gerard Roma","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007303338","display_name":"Andrew Simpson","orcid":"https://orcid.org/0000-0001-6584-6451"},"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":"Andrew J.R. Simpson","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066967599","display_name":"Mark D. Plumbley","orcid":"https://orcid.org/0000-0002-9708-1075"},"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 D. Plumbley","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5013467271"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":4.5823,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.95511995,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3339","last_page":"3343"},"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":0.9994999766349792,"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":0.9977999925613403,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.8079197406768799},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.755986750125885},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6855542659759521},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6796788573265076},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.6252736449241638},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5409896969795227},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5236156582832336},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4264991283416748},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4145057797431946},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3482432961463928},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33460134267807007},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1446734070777893},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12352773547172546},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.0576058030128479},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.05580037832260132}],"concepts":[{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.8079197406768799},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.755986750125885},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6855542659759521},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6796788573265076},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.6252736449241638},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5409896969795227},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5236156582832336},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4264991283416748},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4145057797431946},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3482432961463928},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33460134267807007},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1446734070777893},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12352773547172546},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0576058030128479},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.05580037832260132},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2016-216","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-216","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"},{"id":"pmh:oai:alma.44SUR_INST:11140033060002346","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:epubs.surrey.ac.uk:811087","is_oa":false,"landing_page_url":"http://epubs.surrey.ac.uk/811087/1/216_Paper.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":[],"awards":[{"id":"https://openalex.org/G1934935867","display_name":null,"funder_award_id":"Engineering and Physical Sciences R","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3420410296","display_name":"Musical Audio Repurposing using Source Separation","funder_award_id":"EP/L027119/2","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5929590225","display_name":"Musical Audio Repurposing using Source Separation","funder_award_id":"EP/L027119/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6513227722","display_name":null,"funder_award_id":"EP/L027119/2","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G740539323","display_name":null,"funder_award_id":"EP/L027119/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8452545418","display_name":null,"funder_award_id":"unknown","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":29,"referenced_works":["https://openalex.org/W66912011","https://openalex.org/W141691577","https://openalex.org/W1482149378","https://openalex.org/W1606347560","https://openalex.org/W1990322717","https://openalex.org/W1997917263","https://openalex.org/W2016944307","https://openalex.org/W2031647436","https://openalex.org/W2046869671","https://openalex.org/W2053165762","https://openalex.org/W2064949872","https://openalex.org/W2098950531","https://openalex.org/W2127851351","https://openalex.org/W2128073546","https://openalex.org/W2135293965","https://openalex.org/W2138245448","https://openalex.org/W2141411743","https://openalex.org/W2146544734","https://openalex.org/W2150415460","https://openalex.org/W2155531311","https://openalex.org/W2324972235","https://openalex.org/W2397521518","https://openalex.org/W2398306137","https://openalex.org/W2405258286","https://openalex.org/W2515826317","https://openalex.org/W2917831833","https://openalex.org/W4231109964","https://openalex.org/W4234892472","https://openalex.org/W4252684946"],"related_works":["https://openalex.org/W2375786911","https://openalex.org/W2328889547","https://openalex.org/W2367630196","https://openalex.org/W756944427","https://openalex.org/W2349547031","https://openalex.org/W3003858543","https://openalex.org/W1969547578","https://openalex.org/W4312306082","https://openalex.org/W2358871510","https://openalex.org/W1998497505"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"(DNNs)":[3],"are":[4,23],"usually":[5],"used":[6,24],"for":[7],"single":[8],"channel":[9],"source":[10],"separation":[11],"to":[12,25,52,56,65,80],"predict":[13],"either":[14],"soft":[15,45,63,104],"or":[16],"binary":[17,61,102,123],"time":[18],"frequency":[19],"masks.":[20,46],"The":[21],"masks":[22,34,64,105],"separate":[26],"the":[27,30,58,67,71,99,122],"sources":[28,37,83],"from":[29],"mixed":[31],"signal.":[32],"Binary":[33],"produce":[35],"separated":[36,82],"with":[38,84],"more":[39],"distortion":[40,86,110],"and":[41,62,69,87,103,116],"less":[42],"interference":[43,89,120],"than":[44,111],"In":[47],"this":[48],"paper,":[49],"we":[50],"propose":[51],"use":[53],"another":[54],"DNN":[55,107],"combine":[57],"estimates":[59,100],"of":[60,73,101],"achieve":[66,81],"advantages":[68],"avoid":[70],"disadvantages":[72],"using":[74,106,112],"each":[75,91,113],"mask":[76],"individually.":[77],"We":[78],"aim":[79],"low":[85,88,119],"between":[90],"other.":[92],"Our":[93],"experimental":[94],"results":[95],"show":[96],"that":[97],"combining":[98],"achieves":[108,117],"lower":[109],"estimate":[114],"individually":[115],"as":[118,121],"mask.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":8}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}