{"id":"https://openalex.org/W3008132750","doi":"https://doi.org/10.1109/isspit47144.2019.9001837","title":"Singing Voice Separation Based on Deep Regression Neural Network","display_name":"Singing Voice Separation Based on Deep Regression Neural Network","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3008132750","doi":"https://doi.org/10.1109/isspit47144.2019.9001837","mag":"3008132750"},"language":"en","primary_location":{"id":"doi:10.1109/isspit47144.2019.9001837","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isspit47144.2019.9001837","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)","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/A5018882232","display_name":"Shuqian Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuqian Yang","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100692904","display_name":"Wei-Qiang Zhang","orcid":"https://orcid.org/0000-0003-3841-1959"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Qiang Zhang","raw_affiliation_strings":["Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5018882232"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.6634,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70639499,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"21","issue":null,"first_page":"1","last_page":"5"},"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":0.9991999864578247,"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/singing","display_name":"Singing","score":0.9314563274383545},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.7517604827880859},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.7014836668968201},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6493165493011475},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6219836473464966},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6072797775268555},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4466811418533325},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.4421471655368805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41864168643951416},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3383907079696655},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2646295726299286},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.20452958345413208},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12817591428756714},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06631657481193542}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9314563274383545},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.7517604827880859},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.7014836668968201},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6493165493011475},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6219836473464966},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6072797775268555},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4466811418533325},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.4421471655368805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41864168643951416},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3383907079696655},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2646295726299286},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20452958345413208},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12817591428756714},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06631657481193542},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isspit47144.2019.9001837","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isspit47144.2019.9001837","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W258661521","https://openalex.org/W1522301498","https://openalex.org/W1545453738","https://openalex.org/W1584895311","https://openalex.org/W1594771616","https://openalex.org/W1902027874","https://openalex.org/W2022668263","https://openalex.org/W2031767704","https://openalex.org/W2039844283","https://openalex.org/W2044893557","https://openalex.org/W2097361095","https://openalex.org/W2116244429","https://openalex.org/W2125630648","https://openalex.org/W2127851351","https://openalex.org/W2130789253","https://openalex.org/W2152591660","https://openalex.org/W2171000037","https://openalex.org/W2405589348","https://openalex.org/W2669032454","https://openalex.org/W2707788252","https://openalex.org/W2756050682","https://openalex.org/W2916985722","https://openalex.org/W2917831833","https://openalex.org/W2963750251","https://openalex.org/W2963751183","https://openalex.org/W2963992487","https://openalex.org/W2964121744","https://openalex.org/W6609686331","https://openalex.org/W6631190155","https://openalex.org/W6632656686","https://openalex.org/W6635089314","https://openalex.org/W6655028035","https://openalex.org/W6679009796","https://openalex.org/W6713519970","https://openalex.org/W6759212570"],"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/W1964208564","https://openalex.org/W169038075","https://openalex.org/W2103031592","https://openalex.org/W1967226023","https://openalex.org/W2077498359"],"abstract_inverted_index":{"The":[0,76],"goal":[1],"of":[2,41,65,93],"singing":[3,30,94],"voice":[4,31,95],"separation":[5,32],"is":[6],"to":[7,28,56],"separate":[8],"the":[9,12,24,29,39,42,61,73,91],"vocals":[10],"and":[11,34,67],"accompaniments":[13],"from":[14],"a":[15,46],"monaural":[16],"music":[17,66],"mixture.":[18],"In":[19],"this":[20],"paper,":[21],"we":[22],"apply":[23],"speech":[25],"enhancement":[26],"framework":[27],"task":[33],"make":[35],"some":[36],"improvements":[37],"on":[38,51],"architecture":[40,55],"model.":[43],"We":[44,59],"utilize":[45],"nonlinear":[47],"regression":[48,74],"function":[49],"based":[50],"deep":[52],"neural":[53],"network":[54],"extract":[57,60],"accompaniments.":[58],"log-power":[62],"spectral":[63],"features":[64],"use":[68],"five":[69],"ReLU":[70],"layers":[71],"in":[72,79,90],"mode.":[75],"experimental":[77],"results":[78,89],"DSD100":[80],"dataset":[81],"show":[82],"that":[83],"our":[84],"method":[85],"can":[86],"achieve":[87],"good":[88],"field":[92],"separation.":[96]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}