{"id":"https://openalex.org/W2625041691","doi":"https://doi.org/10.1109/taslp.2017.2716443","title":"Two-Stage Single-Channel Audio Source Separation Using Deep Neural Networks","display_name":"Two-Stage Single-Channel Audio Source Separation Using Deep Neural Networks","publication_year":2017,"publication_date":"2017-06-16","ids":{"openalex":"https://openalex.org/W2625041691","doi":"https://doi.org/10.1109/taslp.2017.2716443","mag":"2625041691"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2017.2716443","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2716443","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/A5013467271","display_name":"Emad M. Grais","orcid":"https://orcid.org/0000-0002-6387-0981"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Emad M. Grais","raw_affiliation_strings":["Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K","institution_ids":[]}]},{"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/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gerard Roma","raw_affiliation_strings":["Centre for Vision, Speech, and Signal Processing, University of Surrey, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech, and Signal Processing, University of Surrey, Atlanta, GA, USA","institution_ids":["https://openalex.org/I4210121626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007303338","display_name":"Andrew Simpson","orcid":"https://orcid.org/0000-0001-6584-6451"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew J. R. Simpson","raw_affiliation_strings":["Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066967599","display_name":"Mark D. Plumbley","orcid":"https://orcid.org/0000-0002-9708-1075"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark D. Plumbley","raw_affiliation_strings":["Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5013467271"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.6637,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.95906831,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"25","issue":"9","first_page":"1773","last_page":"1783"},"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":0.9994000196456909,"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":0.9973999857902527,"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/stage","display_name":"Stage (stratigraphy)","score":0.7342777252197266},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5921320915222168},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5576916933059692},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5327686667442322},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4660096764564514},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4591902792453766},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3954462707042694},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.347262978553772},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.17564189434051514},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.16632452607154846},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11326861381530762}],"concepts":[{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.7342777252197266},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5921320915222168},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5576916933059692},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5327686667442322},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4660096764564514},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4591902792453766},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3954462707042694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.347262978553772},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.17564189434051514},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.16632452607154846},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11326861381530762},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2017.2716443","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2716443","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:alma.44SUR_INST:11139967800002346","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:841432","is_oa":false,"landing_page_url":"http://epubs.surrey.ac.uk/841432/1/Two%20Stage%20Single%20Channel%20Audio%20Source%20Separation%20using%20Deep%20Neural%20Networks.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":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7300000190734863}],"awards":[{"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"}],"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":47,"referenced_works":["https://openalex.org/W141691577","https://openalex.org/W173461423","https://openalex.org/W1482149378","https://openalex.org/W1508756421","https://openalex.org/W1564690189","https://openalex.org/W1790748249","https://openalex.org/W1794826295","https://openalex.org/W1970924839","https://openalex.org/W1985242443","https://openalex.org/W1999736059","https://openalex.org/W2031647436","https://openalex.org/W2035576074","https://openalex.org/W2044893557","https://openalex.org/W2046869671","https://openalex.org/W2049113157","https://openalex.org/W2053165762","https://openalex.org/W2057200980","https://openalex.org/W2064949872","https://openalex.org/W2069681747","https://openalex.org/W2117150818","https://openalex.org/W2124149378","https://openalex.org/W2127758213","https://openalex.org/W2127851351","https://openalex.org/W2135029798","https://openalex.org/W2150415460","https://openalex.org/W2160815625","https://openalex.org/W2197404611","https://openalex.org/W2304609584","https://openalex.org/W2398306137","https://openalex.org/W2398972335","https://openalex.org/W2405258286","https://openalex.org/W2408744528","https://openalex.org/W2508884455","https://openalex.org/W2515826317","https://openalex.org/W2917831833","https://openalex.org/W3124794156","https://openalex.org/W3143596294","https://openalex.org/W4205210034","https://openalex.org/W4231109964","https://openalex.org/W4252684946","https://openalex.org/W6607099979","https://openalex.org/W6630493826","https://openalex.org/W6633740391","https://openalex.org/W6677513291","https://openalex.org/W6680012447","https://openalex.org/W6712656540","https://openalex.org/W6713676406"],"related_works":["https://openalex.org/W2071676784","https://openalex.org/W4292513318","https://openalex.org/W2329386257","https://openalex.org/W2503350049","https://openalex.org/W4308092240","https://openalex.org/W2287611352","https://openalex.org/W320684304","https://openalex.org/W1509352139","https://openalex.org/W2791440692","https://openalex.org/W2077498359"],"abstract_inverted_index":{"Most":[0],"single":[1,112,178],"channel":[2],"audio":[3],"source":[4,89],"separation":[5,153],"approaches":[6],"produce":[7],"separated":[8,39,52,77,88,105,121,142,159,167],"sources":[9,15,28,37,53,78,106,168,175],"accompanied":[10],"by":[11,161],"interference":[12,49,136,164],"from":[13,40],"other":[14,17],"and":[16,54,137,169],"distortions.":[18],"To":[19,114],"tackle":[20],"this":[21],"problem,":[22],"we":[23],"propose":[24,65],"to":[25,71,132,172],"separate":[26],"the":[27,33,36,41,45,48,51,55,73,76,80,84,100,104,117,120,123,126,135,138,141,155,158,163,166,174],"in":[29,79,99,125],"two":[30,66,150],"stages.":[31],"In":[32,44,83],"first":[34,85],"stage,":[35,47],"are":[38,57,107,129],"mixed":[42],"signal.":[43],"second":[46,81,101,127],"between":[50,165],"distortions":[56,139,170],"reduced":[58],"using":[59,93,110,149,176],"deep":[60],"neural":[61],"networks":[62],"(DNNs).":[63],"We":[64],"methods":[67],"that":[68,148],"use":[69],"DNNs":[70,124],"improve":[72,116],"quality":[74,118,156],"of":[75,119,140,152,157,180],"stage.":[82],"method,":[86],"each":[87],"is":[90],"improved":[91,108],"individually":[92],"its":[94],"own":[95],"trained":[96,130],"DNN,":[97],"while":[98],"method":[102],"all":[103],"together":[109],"a":[111,177],"DNN.":[113],"further":[115,133],"sources,":[122],"stage":[128,179],"discriminatively":[131],"decrease":[134],"sources.":[143],"Our":[144],"experimental":[145],"results":[146],"show":[147],"stages":[151],"improves":[154],"signals":[160],"decreasing":[162],"compared":[171],"separating":[173],"separation.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
