{"id":"https://openalex.org/W3100868860","doi":"https://doi.org/10.1631/fitee.2000019","title":"Latent source-specific generative factor learning for monaural speech separation using weighted-factor autoencoder","display_name":"Latent source-specific generative factor learning for monaural speech separation using weighted-factor autoencoder","publication_year":2020,"publication_date":"2020-11-01","ids":{"openalex":"https://openalex.org/W3100868860","doi":"https://doi.org/10.1631/fitee.2000019","mag":"3100868860"},"language":"en","primary_location":{"id":"doi:10.1631/fitee.2000019","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.2000019","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology & Electronic Engineering","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/A5101969936","display_name":"Jing\u2010jing Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing-jing Chen","raw_affiliation_strings":["School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, 212013, China"],"raw_orcid":"https://orcid.org/0000-0003-2968-0313","affiliations":[{"raw_affiliation_string":"School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, 212013, China","institution_ids":["https://openalex.org/I115592961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068470372","display_name":"Qirong Mao","orcid":"https://orcid.org/0000-0002-0616-4431"},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]},{"id":"https://openalex.org/I4210096899","display_name":"Jiangsu University of Science and Technology","ror":"https://ror.org/00tyjp878","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210096899"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi-rong Mao","raw_affiliation_strings":["Jiangsu Key Laboratory of Security Technology for Industrial Cyberspace, Zhenjiang, 212013, China","School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, 212013, China"],"raw_orcid":"https://orcid.org/0000-0002-0616-4431","affiliations":[{"raw_affiliation_string":"Jiangsu Key Laboratory of Security Technology for Industrial Cyberspace, Zhenjiang, 212013, China","institution_ids":["https://openalex.org/I4210096899"]},{"raw_affiliation_string":"School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, 212013, China","institution_ids":["https://openalex.org/I115592961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064159772","display_name":"You-cai Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"You-cai Qin","raw_affiliation_strings":["School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, 212013, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, 212013, China","institution_ids":["https://openalex.org/I115592961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034371072","display_name":"Shuangqing Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuang-qing Qian","raw_affiliation_strings":["School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, 212013, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, 212013, China","institution_ids":["https://openalex.org/I115592961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063280269","display_name":"Zhishen Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi-shen Zheng","raw_affiliation_strings":["School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, 212013, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, 212013, China","institution_ids":["https://openalex.org/I115592961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14056011,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"21","issue":"11","first_page":"1639","last_page":"1650"},"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":0.9997000098228455,"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":0.9993000030517578,"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/monaural","display_name":"Monaural","score":0.8982400894165039},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7935630083084106},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.642858624458313},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5004875659942627},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49377521872520447},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4899968206882477},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.45986342430114746},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39112815260887146},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37287086248397827},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.24707496166229248},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2394910752773285}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.8982400894165039},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7935630083084106},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.642858624458313},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5004875659942627},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49377521872520447},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4899968206882477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45986342430114746},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39112815260887146},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37287086248397827},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.24707496166229248},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2394910752773285},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1631/fitee.2000019","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.2000019","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Information Technology & Electronic Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W185399533","https://openalex.org/W1482149378","https://openalex.org/W1494198834","https://openalex.org/W1528056001","https://openalex.org/W1635512741","https://openalex.org/W1964538581","https://openalex.org/W1981463705","https://openalex.org/W2031647436","https://openalex.org/W2044222806","https://openalex.org/W2061074721","https://openalex.org/W2069681747","https://openalex.org/W2088361146","https://openalex.org/W2123649031","https://openalex.org/W2124149378","https://openalex.org/W2127851351","https://openalex.org/W2130322773","https://openalex.org/W2187089797","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2561557072","https://openalex.org/W2578331995","https://openalex.org/W2605138598","https://openalex.org/W2661910912","https://openalex.org/W2734774145","https://openalex.org/W2789367656","https://openalex.org/W2794289187","https://openalex.org/W2889205417","https://openalex.org/W2899023680","https://openalex.org/W2902458453","https://openalex.org/W2952218014","https://openalex.org/W2962850167","https://openalex.org/W2969873628","https://openalex.org/W2986487674","https://openalex.org/W3015199127","https://openalex.org/W3099330747","https://openalex.org/W4233392025","https://openalex.org/W4256399001","https://openalex.org/W6665565033","https://openalex.org/W6684458083"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1518859147","https://openalex.org/W1974981856","https://openalex.org/W2045506488","https://openalex.org/W1983045063","https://openalex.org/W4321794819","https://openalex.org/W2072124114","https://openalex.org/W2944394647","https://openalex.org/W1543248128"],"abstract_inverted_index":{"Much":[0],"recent":[1],"progress":[2],"in":[3,68,89,112],"monaural":[4],"speech":[5],"separation":[6,114],"(MSS)":[7],"has":[8,155],"been":[9],"achieved":[10],"through":[11],"a":[12,39,43,76,86,103,108,123,159],"series":[13],"of":[14,47,57,125,150],"deep":[15],"learning":[16],"architectures":[17],"based":[18],"on":[19,137,158],"autoencoders,":[20],"which":[21,84],"use":[22],"an":[23],"encoder":[24],"to":[25,41,93,132],"condense":[26],"the":[27,58,90,113,145],"input":[28,60],"signal":[29],"into":[30,38],"compressed":[31],"features":[32,37,127],"and":[33,107,122],"then":[34],"feed":[35],"these":[36,50],"decoder":[40],"construct":[42,64],"specific":[44],"audio":[45,66],"source":[46,67,96,110],"interest.":[48],"However,":[49],"approaches":[51],"can":[52,117],"neither":[53],"learn":[54,118],"generative":[55,120],"factors":[56,121],"original":[59],"for":[61,82,128],"MSS":[62,133,162],"nor":[63],"each":[65,129],"mixed":[69],"speech.":[70],"In":[71,148],"this":[72],"study,":[73],"we":[74],"propose":[75],"novel":[77],"weighted-factor":[78],"autoencoder":[79],"(WFAE)":[80],"model":[81],"MSS,":[83],"introduces":[85],"regularization":[87],"loss":[88],"objective":[91],"function":[92],"isolate":[94],"one":[95],"without":[97],"containing":[98],"other":[99],"sources.":[100],"By":[101],"incorporating":[102],"latent":[104],"attention":[105],"mechanism":[106],"supervised":[109],"constructor":[111],"layer,":[115],"WFAE":[116,154],"source-specific":[119],"set":[124],"discriminative":[126],"source,":[130],"leading":[131],"performance":[134],"improvement.":[135],"Experiments":[136],"benchmark":[138],"datasets":[139],"show":[140],"that":[141],"our":[142],"approach":[143],"outperforms":[144],"existing":[146],"methods.":[147],"terms":[149],"three":[151],"important":[152],"metrics,":[153],"great":[156],"success":[157],"relatively":[160],"challenging":[161],"case,":[163],"i.e.,":[164],"speaker-independent":[165],"MSS.":[166]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}