{"id":"https://openalex.org/W2810535283","doi":"https://doi.org/10.1109/taslp.2018.2851151","title":"Deep Learning Based Speech Separation via NMF-Style Reconstructions","display_name":"Deep Learning Based Speech Separation via NMF-Style Reconstructions","publication_year":2018,"publication_date":"2018-07-02","ids":{"openalex":"https://openalex.org/W2810535283","doi":"https://doi.org/10.1109/taslp.2018.2851151","mag":"2810535283"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2851151","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2851151","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/A5068044387","display_name":"Shuai Nie","orcid":"https://orcid.org/0000-0002-8078-6829"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuai Nie","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108575841","display_name":"Shan Liang","orcid":"https://orcid.org/0000-0002-9734-9166"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan Liang","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039635290","display_name":"Wenju Liu","orcid":"https://orcid.org/0000-0001-9088-8282"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenju Liu","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693230","display_name":"Xueliang Zhang","orcid":"https://orcid.org/0000-0002-0406-1105"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueliang Zhang","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Huhhot, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Huhhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5068044387"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"],"apc_list":null,"apc_paid":null,"fwci":3.468,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.93681628,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"26","issue":"11","first_page":"2043","last_page":"2055"},"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/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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"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/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.9065905809402466},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8882412910461426},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7100162506103516},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6951549649238586},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6139942407608032},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6035870909690857},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5770545601844788},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5314903259277344},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5310521721839905},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.5175475478172302},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5132710933685303},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5093970894813538},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.46886923909187317},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.429992139339447},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.426870733499527},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21777001023292542},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.17174193263053894},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14351218938827515}],"concepts":[{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.9065905809402466},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8882412910461426},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7100162506103516},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6951549649238586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6139942407608032},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6035870909690857},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5770545601844788},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5314903259277344},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5310521721839905},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.5175475478172302},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5132710933685303},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5093970894813538},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.46886923909187317},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.429992139339447},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.426870733499527},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21777001023292542},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.17174193263053894},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14351218938827515},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2018.2851151","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2851151","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G2903800947","display_name":null,"funder_award_id":"91120303","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3417613999","display_name":null,"funder_award_id":"61503382","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5893652795","display_name":null,"funder_award_id":"61425017","funder_id":"https://openalex.org/F4320336125","funder_display_name":"National Science Fund for Distinguished Young Scholars"},{"id":"https://openalex.org/G6415194035","display_name":null,"funder_award_id":"61403370","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6634446941","display_name":null,"funder_award_id":"61273267","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8987289441","display_name":null,"funder_award_id":"61573357","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320315072","display_name":"Mitsubishi Electric Research Laboratories","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336125","display_name":"National Science Fund for Distinguished Young Scholars","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1495679096","https://openalex.org/W1516630152","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1555814299","https://openalex.org/W1635512741","https://openalex.org/W1790748249","https://openalex.org/W1794826295","https://openalex.org/W1902027874","https://openalex.org/W1963970749","https://openalex.org/W1970924839","https://openalex.org/W1974387177","https://openalex.org/W1981755271","https://openalex.org/W1999736059","https://openalex.org/W2006129368","https://openalex.org/W2013608223","https://openalex.org/W2016891207","https://openalex.org/W2017288758","https://openalex.org/W2027701650","https://openalex.org/W2031647436","https://openalex.org/W2031696998","https://openalex.org/W2039844283","https://openalex.org/W2042750879","https://openalex.org/W2044893557","https://openalex.org/W2046869671","https://openalex.org/W2057200980","https://openalex.org/W2060822897","https://openalex.org/W2062470211","https://openalex.org/W2064949872","https://openalex.org/W2069681747","https://openalex.org/W2070707809","https://openalex.org/W2077799289","https://openalex.org/W2078528584","https://openalex.org/W2085149143","https://openalex.org/W2085191029","https://openalex.org/W2087126002","https://openalex.org/W2100495367","https://openalex.org/W2104104263","https://openalex.org/W2113131123","https://openalex.org/W2124149378","https://openalex.org/W2127851351","https://openalex.org/W2128653836","https://openalex.org/W2135029798","https://openalex.org/W2141998673","https://openalex.org/W2150415460","https://openalex.org/W2158291955","https://openalex.org/W2158331493","https://openalex.org/W2160215673","https://openalex.org/W2168379380","https://openalex.org/W2168793898","https://openalex.org/W2259731387","https://openalex.org/W2344535577","https://openalex.org/W2396837968","https://openalex.org/W2401527147","https://openalex.org/W2405589348","https://openalex.org/W2513910579","https://openalex.org/W2587994092","https://openalex.org/W2619993508","https://openalex.org/W2625041691","https://openalex.org/W2962949994","https://openalex.org/W2964121744","https://openalex.org/W2964199361","https://openalex.org/W3124794156","https://openalex.org/W3127686677","https://openalex.org/W3143596294","https://openalex.org/W4253928870","https://openalex.org/W6631190155","https://openalex.org/W6680012447","https://openalex.org/W6683202405","https://openalex.org/W6684458083","https://openalex.org/W6692000528","https://openalex.org/W6712586757","https://openalex.org/W6713519970","https://openalex.org/W6726357283","https://openalex.org/W6733667431"],"related_works":["https://openalex.org/W2123043102","https://openalex.org/W2577807713","https://openalex.org/W2098101267","https://openalex.org/W2037504162","https://openalex.org/W2774154397","https://openalex.org/W2921513691","https://openalex.org/W1979654135","https://openalex.org/W2156699640","https://openalex.org/W2081322759","https://openalex.org/W2156181515"],"abstract_inverted_index":{"Deep":[0],"learning":[1,42,58],"based":[2],"speech":[3,81,106,130,186],"separation":[4,19,22,82,157],"usually":[5],"uses":[6],"a":[7,12,39,66,84,92,121,173],"supervised":[8],"algorithm":[9],"to":[10,18,96,111,123,180],"learn":[11,112],"mapping":[13],"function":[14],"from":[15],"noisy":[16],"features":[17],"targets.":[20],"These":[21],"targets,":[23],"either":[24],"ideal":[25],"masks":[26],"or":[27],"magnitude":[28,127],"spectrograms,":[29],"have":[30],"prominent":[31],"spectro-temporal":[32],"structures.":[33,52],"Nonnegative":[34],"matrix":[35],"factorization":[36],"(NMF)":[37],"is":[38,45,65,109,142],"well-known":[40],"representation":[41],"technique":[43],"that":[44,116,163,192],"capable":[46],"of":[47,56,100,129,134],"capturing":[48],"the":[49,54,98,113,126,149,164,193,199],"basic":[50],"spectral":[51],"Therefore,":[53],"combination":[55],"deep":[57,74],"and":[59,78,103,131,183],"NMF":[60,79,104,108],"as":[61,144],"an":[62,145,155],"organic":[63],"whole":[64],"smart":[67],"strategy.":[68],"However,":[69],"previous":[70,150,200],"methods":[71],"typically":[72],"use":[73],"neural":[75],"networks":[76],"(DNN)":[77],"for":[80,105],"in":[83,159],"separate":[85],"manner.":[86],"In":[87],"this":[88],"paper,":[89],"we":[90,171],"propose":[91],"jointly":[93],"combinatorial":[94],"scheme":[95],"concentrate":[97],"strengths":[99],"both":[101],"DNN":[102,122,152],"separation.":[107],"used":[110,143],"basis":[114],"spectra":[115],"then":[117],"are":[118,196],"integrated":[119],"into":[120],"directly":[124,153],"reconstruct":[125],"spectrograms":[128],"noise.":[132],"Instead":[133],"predicting":[135],"activation":[136],"coefficients":[137],"inferred":[138],"by":[139,148],"NMF,":[140],"which":[141],"intermediate":[146],"target":[147],"methods,":[151],"optimizes":[154],"actual":[156],"objective":[158,176],"our":[160],"system,":[161],"so":[162],"accumulated":[165],"errors":[166],"could":[167],"be":[168],"alleviated.":[169],"Moreover,":[170],"explore":[172],"discriminative":[174],"training":[175],"with":[177,198],"sparsity":[178],"constraints":[179],"suppress":[181],"noise":[182],"preserve":[184],"more":[185],"components":[187],"further.":[188],"Systematic":[189],"experiments":[190],"show":[191],"proposed":[194],"models":[195],"competitive":[197],"methods.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}