{"id":"https://openalex.org/W3038106538","doi":"https://doi.org/10.3390/sym12061051","title":"Monaural Singing Voice and Accompaniment Separation Based on Gated Nested U-Net Architecture","display_name":"Monaural Singing Voice and Accompaniment Separation Based on Gated Nested U-Net Architecture","publication_year":2020,"publication_date":"2020-06-24","ids":{"openalex":"https://openalex.org/W3038106538","doi":"https://doi.org/10.3390/sym12061051","mag":"3038106538"},"language":"en","primary_location":{"id":"doi:10.3390/sym12061051","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym12061051","pdf_url":"https://www.mdpi.com/2073-8994/12/6/1051/pdf","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2073-8994/12/6/1051/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014090193","display_name":"Haibo Geng","orcid":"https://orcid.org/0000-0003-0168-4830"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haibo Geng","raw_affiliation_strings":["Key Laboratory of Signal Detection and Processing in Xinjiang Uygur Autonomous Region, Urumqi 830046, China","School of Information Science and Engineering, Xinjiang University, Urumqi 830046, China"],"raw_orcid":"https://orcid.org/0000-0003-0168-4830","affiliations":[{"raw_affiliation_string":"Key Laboratory of Signal Detection and Processing in Xinjiang Uygur Autonomous Region, Urumqi 830046, China","institution_ids":[]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi 830046, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042363663","display_name":"Ying Hu","orcid":"https://orcid.org/0000-0001-7505-1767"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ying Hu","raw_affiliation_strings":["Key Laboratory of Signal Detection and Processing in Xinjiang Uygur Autonomous Region, Urumqi 830046, China","School of Information Science and Engineering, Xinjiang University, Urumqi 830046, China"],"raw_orcid":"https://orcid.org/0000-0001-7505-1767","affiliations":[{"raw_affiliation_string":"Key Laboratory of Signal Detection and Processing in Xinjiang Uygur Autonomous Region, Urumqi 830046, China","institution_ids":[]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi 830046, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024772368","display_name":"Hao Huang","orcid":"https://orcid.org/0000-0001-6604-0951"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Huang","raw_affiliation_strings":["Key Laboratory of Multilingual Information Technology in Xinjiang Uygur Autonomous Region, Urumqi 830046, China","School of Information Science and Engineering, Xinjiang University, Urumqi 830046, China"],"raw_orcid":"https://orcid.org/0000-0001-6604-0951","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multilingual Information Technology in Xinjiang Uygur Autonomous Region, Urumqi 830046, China","institution_ids":[]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi 830046, China","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5042363663"],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1479},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1479},"fwci":0.586,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.66559151,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"12","issue":"6","first_page":"1051","last_page":"1051"},"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":0.9998000264167786,"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":0.9987999796867371,"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/computer-science","display_name":"Computer science","score":0.7419870495796204},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5955104827880859},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5604807734489441},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5325523614883423},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5127061605453491},{"id":"https://openalex.org/keywords/net","display_name":"Net (polyhedron)","score":0.503527820110321},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.46335935592651367},{"id":"https://openalex.org/keywords/series","display_name":"Series (stratigraphy)","score":0.44505229592323303},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.423875093460083},{"id":"https://openalex.org/keywords/ideal","display_name":"Ideal (ethics)","score":0.4222082197666168},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3889733850955963},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3887496888637543},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.320866197347641},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.145799458026886}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7419870495796204},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5955104827880859},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5604807734489441},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5325523614883423},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5127061605453491},{"id":"https://openalex.org/C14166107","wikidata":"https://www.wikidata.org/wiki/Q253829","display_name":"Net (polyhedron)","level":2,"score":0.503527820110321},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.46335935592651367},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.44505229592323303},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.423875093460083},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.4222082197666168},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3889733850955963},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3887496888637543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.320866197347641},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.145799458026886},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/sym12061051","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym12061051","pdf_url":"https://www.mdpi.com/2073-8994/12/6/1051/pdf","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:6c7b139df4ba45208f6f5e05620a5b01","is_oa":true,"landing_page_url":"https://doaj.org/article/6c7b139df4ba45208f6f5e05620a5b01","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symmetry, Vol 12, Iss 6, p 1051 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/sym12061051","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym12061051","pdf_url":"https://www.mdpi.com/2073-8994/12/6/1051/pdf","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7400000095367432}],"awards":[{"id":"https://openalex.org/G3100194551","display_name":"\u5531\u6b4c\u8f85\u52a9\u7cfb\u7edf\u76f8\u5173\u6280\u672f\u7684\u7814\u7a76","funder_award_id":"61761041","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3931585407","display_name":null,"funder_award_id":"U1903213","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6861194883","display_name":"\u57fa\u4e8e\u65e0\u76d1\u7763\u5b66\u4e60\u65b9\u6cd5\u7684\u53e3\u8bed\u7406\u89e3\u4e0e\u4eba\u673a\u5bf9\u8bdd\u884c\u4e3a\u7814\u7a76","funder_award_id":"61663044","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3038106538.pdf"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1496920063","https://openalex.org/W1594771616","https://openalex.org/W1790748249","https://openalex.org/W1901129140","https://openalex.org/W1964531215","https://openalex.org/W1964544556","https://openalex.org/W2057745663","https://openalex.org/W2064675550","https://openalex.org/W2083667973","https://openalex.org/W2127851351","https://openalex.org/W2134096203","https://openalex.org/W2164098335","https://openalex.org/W2318192700","https://openalex.org/W2394955069","https://openalex.org/W2405258286","https://openalex.org/W2465050681","https://openalex.org/W2514973355","https://openalex.org/W2567070169","https://openalex.org/W2735663686","https://openalex.org/W2774707525","https://openalex.org/W2796571515","https://openalex.org/W2884436604","https://openalex.org/W2897371647","https://openalex.org/W2952339589","https://openalex.org/W2953318193","https://openalex.org/W2962715207","https://openalex.org/W2962866211","https://openalex.org/W2963204961","https://openalex.org/W2963723765","https://openalex.org/W2963970792","https://openalex.org/W2964005873","https://openalex.org/W2964229681","https://openalex.org/W2966723236","https://openalex.org/W2972964474","https://openalex.org/W2973054567","https://openalex.org/W2991361823","https://openalex.org/W3123903546","https://openalex.org/W3124794156","https://openalex.org/W3124972797","https://openalex.org/W4235128394"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1974981856","https://openalex.org/W1518859147","https://openalex.org/W2045506488","https://openalex.org/W1983045063","https://openalex.org/W4321794819","https://openalex.org/W2944394647","https://openalex.org/W2072124114","https://openalex.org/W1543248128"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,15,28,80],"separation":[4],"model":[5,142,160,178],"adopting":[6],"gated":[7,63],"nested":[8,31,58],"U-Net":[9],"(GNU-Net)":[10],"architecture,":[11,52],"which":[12],"is":[13,60],"essentially":[14],"deeply":[16],"supervised":[17],"symmetric":[18],"encoder\u2013decoder":[19],"network":[20,124],"that":[21,157],"can":[22,35,108,179,192],"generate":[23,86],"full-resolution":[24],"feature":[25,42],"maps.":[26],"Through":[27],"series":[29],"of":[30,44,68,74,89,106,118],"skip":[32],"pathways,":[33],"it":[34],"reduce":[36],"the":[37,41,50,54,101,133,188],"semantic":[38],"gap":[39],"between":[40],"maps":[43],"encoder":[45],"and":[46,92,103,125,148,164,184],"decoder":[47],"subnetworks.":[48],"In":[49],"GNU-Net":[51,75],"only":[53,193],"backbone":[55],"not":[56],"including":[57],"part":[59],"applied":[61],"with":[62,100,145,150,197],"linear":[64],"units":[65],"(GLUs)":[66],"instead":[67],"conventional":[69],"convolutional":[70],"networks.":[71],"The":[72,129,154],"outputs":[73],"are":[76],"further":[77],"fed":[78],"into":[79,111],"time-frequency":[81],"(T-F)":[82],"mask":[83,120,127,172],"layer":[84],"to":[85,135,169],"two":[87,96,116],"masks":[88,98],"singing":[90,182],"voice":[91,183],"accompaniment.":[93],"Then,":[94],"those":[95],"estimated":[97],"along":[99],"magnitude":[102],"phase":[104],"spectra":[105],"mixture":[107],"be":[109,136],"transformed":[110],"time-domain":[112],"signals.":[113],"We":[114,138],"explored":[115],"types":[117],"T-F":[119,152],"layer,":[121],"discriminative":[122],"training":[123],"difference":[126],"layer.":[128],"experiment":[130],"results":[131,155],"show":[132],"latter":[134],"better.":[137],"evaluated":[139],"our":[140,158,176],"proposed":[141,159,177],"by":[143],"comparing":[144],"three":[146,189],"models,":[147,163],"also":[149],"ideal":[151,170],"masks.":[153],"demonstrate":[156],"outperforms":[161],"compared":[162,190],"it\u2019s":[165],"performance":[166],"comes":[167],"near":[168],"ratio":[171],"(IRM).":[173],"More":[174],"importantly,":[175],"output":[180],"separated":[181],"accompaniment":[185],"simultaneously,":[186],"while":[187],"models":[191],"separate":[194],"one":[195],"source":[196],"trained":[198],"model.":[199]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}