{"id":"https://openalex.org/W1790748249","doi":"https://doi.org/10.1109/taslp.2015.2468583","title":"Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation","display_name":"Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation","publication_year":2015,"publication_date":"2015-08-14","ids":{"openalex":"https://openalex.org/W1790748249","doi":"https://doi.org/10.1109/taslp.2015.2468583","mag":"1790748249"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2015.2468583","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2468583","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1502.04149","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113913928","display_name":"Po-Sen Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Po-Sen Huang","raw_affiliation_strings":["Clarifai, New York, NY","Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Clarifai, New York, NY","institution_ids":[]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064582903","display_name":"Minje Kim","orcid":"https://orcid.org/0000-0003-3513-8328"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minje Kim","raw_affiliation_strings":["Department of Computer Science, University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038903729","display_name":"Paris Smaragdis","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]},{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paris Smaragdis","raw_affiliation_strings":["Adobe Research, San Francisco, CA, USA","Department of Computer Science, University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research, San Francisco, CA, USA","institution_ids":["https://openalex.org/I1306409833"]},{"raw_affiliation_string":"Department of Computer Science, University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":48.8889,"has_fulltext":false,"cited_by_count":469,"citation_normalized_percentile":{"value":0.99929511,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"23","issue":"12","first_page":"2136","last_page":"2147"},"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":0.9991000294685364,"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":0.9980999827384949,"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/monaural","display_name":"Monaural","score":0.9360784888267517},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7465980648994446},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6981027722358704},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6678214073181152},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5524479746818542},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5491056442260742},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.519069254398346},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.4934183657169342},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48154574632644653},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4530068635940552},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4478592872619629},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4315345883369446},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42003798484802246},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3588497042655945},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35224223136901855},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23958730697631836},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.08565470576286316},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08371132612228394}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.9360784888267517},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7465980648994446},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6981027722358704},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6678214073181152},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5524479746818542},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5491056442260742},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.519069254398346},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.4934183657169342},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48154574632644653},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4530068635940552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4478592872619629},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4315345883369446},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42003798484802246},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3588497042655945},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35224223136901855},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23958730697631836},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.08565470576286316},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08371132612228394},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2015.2468583","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2468583","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"},{"id":"pmh:oai:arXiv.org:1502.04149","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1502.04149","pdf_url":"https://arxiv.org/pdf/1502.04149","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.718.8346","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.718.8346","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://minjekim.com/papers/taslp2015_phuang.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1502.04149","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1502.04149","pdf_url":"https://arxiv.org/pdf/1502.04149","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6800000071525574}],"awards":[{"id":"https://openalex.org/G934873480","display_name":null,"funder_award_id":"W911NF-09-1-0383","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1597158214","https://openalex.org/W1674799117","https://openalex.org/W1726370773","https://openalex.org/W1902027874","https://openalex.org/W1964143424","https://openalex.org/W1987906574","https://openalex.org/W2000359198","https://openalex.org/W2002016907","https://openalex.org/W2013598660","https://openalex.org/W2023331723","https://openalex.org/W2031647436","https://openalex.org/W2044893557","https://openalex.org/W2046869671","https://openalex.org/W2053165762","https://openalex.org/W2064675550","https://openalex.org/W2069681747","https://openalex.org/W2094461119","https://openalex.org/W2099904336","https://openalex.org/W2107743791","https://openalex.org/W2121973264","https://openalex.org/W2124539664","https://openalex.org/W2127851351","https://openalex.org/W2128653836","https://openalex.org/W2135151673","https://openalex.org/W2135823751","https://openalex.org/W2141411743","https://openalex.org/W2141998673","https://openalex.org/W2150355110","https://openalex.org/W2156387975","https://openalex.org/W2159505618","https://openalex.org/W2164098335","https://openalex.org/W2168379380","https://openalex.org/W2184045248","https://openalex.org/W2272200996","https://openalex.org/W2290318471","https://openalex.org/W2399506744","https://openalex.org/W2402901296","https://openalex.org/W2403623315","https://openalex.org/W2405258286","https://openalex.org/W2619993508","https://openalex.org/W2731782018","https://openalex.org/W2964335273","https://openalex.org/W3127686677","https://openalex.org/W3147539069","https://openalex.org/W4233135949","https://openalex.org/W6631439307","https://openalex.org/W6639497327","https://openalex.org/W6679714990","https://openalex.org/W6682889407","https://openalex.org/W6683078286","https://openalex.org/W6696830301","https://openalex.org/W6712781682","https://openalex.org/W6713117669","https://openalex.org/W6713353306","https://openalex.org/W6713676406"],"related_works":["https://openalex.org/W2929481141","https://openalex.org/W2103031592","https://openalex.org/W4375869169","https://openalex.org/W1967226023","https://openalex.org/W2538939196","https://openalex.org/W3013896298","https://openalex.org/W2597829360","https://openalex.org/W2987870598","https://openalex.org/W3097681199","https://openalex.org/W2955471771"],"abstract_inverted_index":{"Monaural":[0],"source":[1,49],"separation":[2,50,93,132,151],"is":[3,11],"important":[4],"for":[5,47,85,107],"many":[6],"real":[7],"world":[8],"applications.":[9],"It":[10],"challenging":[12],"because,":[13],"with":[14,70],"only":[15],"a":[16,76,82],"single":[17],"channel":[18],"of":[19,28,39,64],"information":[20],"available,":[21],"without":[22],"any":[23],"constraints,":[24],"an":[25,71],"infinite":[26],"number":[27],"solutions":[29],"are":[30],"possible.":[31],"In":[32],"this":[33],"paper,":[34],"we":[35,80],"explore":[36,81],"joint":[37,62],"optimization":[38,63],"masking":[40,73],"functions":[41],"and":[42,58,104,113,138,153,156],"deep":[43,66],"recurrent":[44,67],"neural":[45,68,87],"networks":[46,69,88],"monaural":[48],"tasks,":[51,116],"including":[52],"speech":[53,59,108,114,131,161],"separation,":[54,57,109,112],"singing":[55,110,149],"voice":[56,111,150],"denoising.":[60],"The":[61],"the":[65,92,97,101,130,148,160],"extra":[72],"layer":[74],"enforces":[75],"reconstruction":[77],"constraint.":[78],"Moreover,":[79],"discriminative":[83],"criterion":[84],"training":[86],"to":[89,126,144],"further":[90],"enhance":[91],"performance.":[94],"We":[95],"evaluate":[96],"proposed":[98],"system":[99],"on":[100],"TSP,":[102],"MIR-1K,":[103],"TIMIT":[105],"datasets":[106],"denoising":[115,162],"respectively.":[117],"Our":[118],"approaches":[119],"achieve":[120],"2.30-4.98":[121],"dB":[122,135,140],"SDR":[123],"gain":[124,137,142],"compared":[125,143],"NMF":[127,155],"models":[128,146],"in":[129,147,159],"task,":[133,152],"2.30-2.48":[134],"GNSDR":[136],"4.32-5.42":[139],"GSIR":[141],"existing":[145],"outperform":[154],"DNN":[157],"baselines":[158],"task.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":30},{"year":2022,"cited_by_count":50},{"year":2021,"cited_by_count":59},{"year":2020,"cited_by_count":56},{"year":2019,"cited_by_count":60},{"year":2018,"cited_by_count":81},{"year":2017,"cited_by_count":62},{"year":2016,"cited_by_count":27},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}