{"id":"https://openalex.org/W2695081499","doi":"https://doi.org/10.1109/icassp.2017.7952159","title":"Supervised source enhancement composed of nonnegative auto-encoders and complementarity subtraction","display_name":"Supervised source enhancement composed of nonnegative auto-encoders and complementarity subtraction","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2695081499","doi":"https://doi.org/10.1109/icassp.2017.7952159","mag":"2695081499"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7952159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5046170826","display_name":"Kenta Niwa","orcid":"https://orcid.org/0000-0002-6911-0238"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kenta Niwa","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101503856","display_name":"Yuma Koizumi","orcid":"https://orcid.org/0000-0003-3645-6213"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuma Koizumi","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002983657","display_name":"Tomoko Kawase","orcid":"https://orcid.org/0000-0002-0670-3319"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoko Kawase","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109046289","display_name":"Kazunori Kobayashi","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazunori Kobayashi","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069841141","display_name":"Yusuke Hioka","orcid":"https://orcid.org/0000-0003-3380-9677"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Yusuke Hioka","raw_affiliation_strings":["Department of Mechanical Engineering, University of Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, University of Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.747,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70772485,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"313","issue":null,"first_page":"266","last_page":"270"},"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.8600092530250549},{"id":"https://openalex.org/keywords/complementarity","display_name":"Complementarity (molecular biology)","score":0.6051924228668213},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6041589975357056},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5931493043899536},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5445031523704529},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5030588507652283},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.49129241704940796},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.47453129291534424},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.4377990961074829},{"id":"https://openalex.org/keywords/subtraction","display_name":"Subtraction","score":0.4330449104309082},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.42734748125076294},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4107819199562073},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3954841196537018},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37099599838256836},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36858922243118286},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2079671025276184},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1969291865825653},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1898157000541687},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.07129916548728943}],"concepts":[{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.8600092530250549},{"id":"https://openalex.org/C202269582","wikidata":"https://www.wikidata.org/wiki/Q2644277","display_name":"Complementarity (molecular biology)","level":2,"score":0.6051924228668213},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6041589975357056},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5931493043899536},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5445031523704529},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5030588507652283},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.49129241704940796},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.47453129291534424},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.4377990961074829},{"id":"https://openalex.org/C68060419","wikidata":"https://www.wikidata.org/wiki/Q40754","display_name":"Subtraction","level":2,"score":0.4330449104309082},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.42734748125076294},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4107819199562073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3954841196537018},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37099599838256836},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36858922243118286},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2079671025276184},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1969291865825653},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1898157000541687},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.07129916548728943},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/icassp.2017.7952159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W653761051","https://openalex.org/W1246381107","https://openalex.org/W1544785557","https://openalex.org/W1562552815","https://openalex.org/W1604717235","https://openalex.org/W1902027874","https://openalex.org/W1931312565","https://openalex.org/W1973746598","https://openalex.org/W1981617403","https://openalex.org/W2005981242","https://openalex.org/W2039844283","https://openalex.org/W2066460453","https://openalex.org/W2099655464","https://openalex.org/W2100495367","https://openalex.org/W2104298926","https://openalex.org/W2116064496","https://openalex.org/W2136922672","https://openalex.org/W2144244295","https://openalex.org/W2149693148","https://openalex.org/W2153935449","https://openalex.org/W2159158911","https://openalex.org/W2397539537","https://openalex.org/W2400027214","https://openalex.org/W2400481151","https://openalex.org/W2468525508","https://openalex.org/W2533784503","https://openalex.org/W2537243027","https://openalex.org/W4231109964","https://openalex.org/W4300402905"],"related_works":["https://openalex.org/W2547262076","https://openalex.org/W1565566036","https://openalex.org/W2563421448","https://openalex.org/W2774154397","https://openalex.org/W2919389044","https://openalex.org/W2921513691","https://openalex.org/W2534043196","https://openalex.org/W1997528538","https://openalex.org/W2777466939","https://openalex.org/W2098101267"],"abstract_inverted_index":{"A":[0],"method":[1,74,114],"for":[2,8,38,115,136],"constructing":[3],"deep":[4],"neural":[5],"networks":[6],"(DNNs)":[7],"accurate":[9,58],"supervised":[10],"source":[11,39,99],"enhancement":[12],"is":[13],"proposed.":[14],"Attempts":[15],"were":[16,65],"made":[17],"in":[18,139],"previous":[19],"studies":[20],"to":[21,34,56,92],"estimate":[22,35],"the":[23,42,62,126],"power":[24],"spectral":[25,103],"densities":[26],"(PSDs)":[27],"of":[28,44],"sound":[29],"sources,":[30],"which":[31,97],"are":[32,89],"used":[33],"Wiener":[36],"filters":[37],"enhancement,":[40],"from":[41],"output":[43],"multiple":[45],"beamformings":[46],"using":[47],"DNNs.":[48],"Although":[49],"performance":[50],"improved,":[51],"it":[52,122],"was":[53,123],"not":[54],"possible":[55],"guarantee":[57],"PSD":[59],"estimation":[60],"since":[61],"trained":[63],"DNNs":[64],"treated":[66],"as":[67],"black":[68],"boxes.":[69],"The":[70],"proposed":[71],"DNN":[72],"construction":[73],"uses":[75],"non-negative":[76,90,93,102],"auto-encoders":[77,86],"and":[78,105],"complementarity":[79,112],"subtraction.":[80],"This":[81],"study":[82],"also":[83],"reveals":[84],"that":[85,125],"whose":[87],"weights":[88],"correspond":[91],"matrix":[94],"factorization":[95],"(NMF),":[96],"decomposes":[98],"PSDs":[100,117],"into":[101],"bases":[104],"their":[106],"activations.":[107],"It":[108],"further":[109],"introduces":[110],"a":[111],"subtraction":[113],"estimating":[116],"accurately.":[118],"Through":[119],"several":[120],"experiments,":[121],"confirmed":[124],"signal-to-interference":[127],"plus":[128],"noise":[129],"ratio":[130],"improved":[131],"by":[132],"approximately":[133],"12":[134],"dB":[135],"datasets":[137],"captured":[138],"various":[140],"noisy/reverberant":[141],"rooms.":[142]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}