{"id":"https://openalex.org/W2031647436","doi":"https://doi.org/10.1109/icassp.2014.6853860","title":"Deep learning for monaural speech separation","display_name":"Deep learning for monaural speech separation","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2031647436","doi":"https://doi.org/10.1109/icassp.2014.6853860","mag":"2031647436"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6853860","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853860","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5113589954","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"]},{"id":"https://openalex.org/I16820183","display_name":"Illinois College","ror":"https://ror.org/02ys5x139","country_code":"US","type":"education","lineage":["https://openalex.org/I16820183"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Po-Sen Huang","raw_affiliation_strings":["University of Illinois College of Law, Champaign, IL, US","Dept of Electr. & Comput. Engg, Univ. of Illinois at Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois College of Law, Champaign, IL, US","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I16820183"]},{"raw_affiliation_string":"Dept of Electr. & Comput. Engg, Univ. 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, USA","[Dept. 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, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"[Dept. 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, USA","Dept of Electr. & Comput. Engg, Univ. 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, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Dept of Electr. & Comput. Engg, Univ. 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/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":["Department of Computer Science, University of Illinois at Urbana-Champaign, USA","Dept of Electr. & Comput. Engg, Univ. 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, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Dept of Electr. & Comput. Engg, Univ. 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":null,"has_fulltext":false,"cited_by_count":436,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1562","last_page":"1566"},"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":0.9991000294685364,"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":0.9968000054359436,"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":0.9454587697982788},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7952386736869812},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.689551830291748},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6414765119552612},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6280026435852051},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5812562108039856},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5696230530738831},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5286065936088562},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5212136507034302},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5050738453865051},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.41756510734558105},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3692140281200409},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3347417116165161},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.0942247211933136},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07874107360839844}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.9454587697982788},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7952386736869812},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.689551830291748},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6414765119552612},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6280026435852051},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5812562108039856},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5696230530738831},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5286065936088562},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5212136507034302},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5050738453865051},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.41756510734558105},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3692140281200409},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3347417116165161},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.0942247211933136},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07874107360839844},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2014.6853860","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853860","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.642.1937","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.642.1937","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.isle.illinois.edu/sst/pubs/2014/huang14icassp.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.718.2664","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.718.2664","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/icassp2014_phuang.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1513606575","https://openalex.org/W1902027874","https://openalex.org/W1994935303","https://openalex.org/W2013598660","https://openalex.org/W2016589492","https://openalex.org/W2100495367","https://openalex.org/W2107743791","https://openalex.org/W2115730999","https://openalex.org/W2127851351","https://openalex.org/W2133340843","https://openalex.org/W2135151673","https://openalex.org/W2136189984","https://openalex.org/W2141411743","https://openalex.org/W2156387975","https://openalex.org/W2164098335","https://openalex.org/W2168379380","https://openalex.org/W2290318471","https://openalex.org/W4233135949","https://openalex.org/W6679714990","https://openalex.org/W6680450716","https://openalex.org/W6682889407"],"related_works":["https://openalex.org/W2929481141","https://openalex.org/W2103031592","https://openalex.org/W1967226023","https://openalex.org/W3013896298","https://openalex.org/W2987870598","https://openalex.org/W3097681199","https://openalex.org/W2892198678","https://openalex.org/W2902298602","https://openalex.org/W2955471771","https://openalex.org/W2098198482"],"abstract_inverted_index":{"Monaural":[0],"source":[1],"separation":[2,68,83],"is":[3,11],"useful":[4],"for":[5,22,60,79],"many":[6],"real-world":[7],"applications":[8],"though":[9],"it":[10],"a":[12,50,56,80],"challenging":[13],"problem.":[14],"In":[15],"this":[16],"paper,":[17],"we":[18,54],"study":[19],"deep":[20,33],"learning":[21,34],"monaural":[23,81],"speech":[24,77,82],"separation.":[25],"We":[26,70],"propose":[27],"the":[28,32,61,67,75],"joint":[29],"optimization":[30],"of":[31],"models":[35,87],"(deep":[36],"neural":[37,41,62],"networks":[38,63],"and":[39,102],"recurrent":[40],"networks)":[42],"with":[43],"an":[44],"extra":[45],"masking":[46],"layer,":[47],"which":[48],"enforces":[49],"reconstruction":[51],"constraint.":[52],"Moreover,":[53],"explore":[55],"discriminative":[57],"training":[58],"criterion":[59],"to":[64,95],"further":[65],"enhance":[66],"performance.":[69],"evaluate":[71],"our":[72],"approaches":[73],"using":[74],"TIMIT":[76],"corpus":[78],"task.":[84],"Our":[85],"proposed":[86],"achieve":[88],"about":[89],"3.8\u223c4.9":[90],"dB":[91],"SIR":[92],"gain":[93],"compared":[94],"NMF":[96],"models,":[97],"while":[98],"maintaining":[99],"better":[100],"SDRs":[101],"SARs.":[103]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":32},{"year":2021,"cited_by_count":48},{"year":2020,"cited_by_count":56},{"year":2019,"cited_by_count":52},{"year":2018,"cited_by_count":55},{"year":2017,"cited_by_count":45},{"year":2016,"cited_by_count":38},{"year":2015,"cited_by_count":37},{"year":2014,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}