{"id":"https://openalex.org/W2046869671","doi":"https://doi.org/10.1109/globalsip.2014.7032183","title":"Discriminatively trained recurrent neural networks for single-channel speech separation","display_name":"Discriminatively trained recurrent neural networks for single-channel speech separation","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2046869671","doi":"https://doi.org/10.1109/globalsip.2014.7032183","mag":"2046869671"},"language":"en","primary_location":{"id":"doi:10.1109/globalsip.2014.7032183","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globalsip.2014.7032183","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/72552/72552.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016747567","display_name":"Felix Weninger","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Weninger","raw_affiliation_strings":["Machine Intelligence & Signal Processing Group (MISP), Technische Universitat Munchen, Munich, Germany","Machine Intelligence & Signal Processing Group (MISP), Technische Universit\u00e4t M\u00fcnchen, 80290 Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Intelligence & Signal Processing Group (MISP), Technische Universitat Munchen, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Machine Intelligence & Signal Processing Group (MISP), Technische Universit\u00e4t M\u00fcnchen, 80290 Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112763337","display_name":"John R. Hershey","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John R. Hershey","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA 02139, USA","Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, 02139 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, 02139 USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076453358","display_name":"Jonathan Le Roux","orcid":"https://orcid.org/0000-0002-3451-171X"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Le Roux","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, 02139 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, 02139 USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bjorn Schuller","raw_affiliation_strings":["Machine Intelligence & Signal Processing Group (MISP), Technische Universitat Munchen, Munich, Germany","Machine Intelligence & Signal Processing Group (MISP), Technische Universit\u00e4t M\u00fcnchen, 80290 Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Intelligence & Signal Processing Group (MISP), Technische Universitat Munchen, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Machine Intelligence & Signal Processing Group (MISP), Technische Universit\u00e4t M\u00fcnchen, 80290 Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":294,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"577","last_page":"581"},"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":0.9994999766349792,"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":0.9991000294685364,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8741118907928467},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7544779777526855},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6813773512840271},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.593707263469696},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5513104796409607},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5492404699325562},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5410818457603455},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5095365643501282},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.4791514277458191},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.46393850445747375},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.45447832345962524},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4375686049461365},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4214513897895813},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.32704252004623413}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8741118907928467},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7544779777526855},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6813773512840271},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.593707263469696},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5513104796409607},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5492404699325562},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5410818457603455},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5095365643501282},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.4791514277458191},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.46393850445747375},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.45447832345962524},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4375686049461365},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4214513897895813},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.32704252004623413},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/globalsip.2014.7032183","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globalsip.2014.7032183","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","raw_type":"proceedings-article"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:72552","is_oa":true,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/72552","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/72552/72552.pdf","source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"}],"best_oa_location":{"id":"pmh:oai:uni-augsburg.opus-bayern.de:72552","is_oa":true,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/72552","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/72552/72552.pdf","source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"},"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2046869671.pdf"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W146976060","https://openalex.org/W299739017","https://openalex.org/W304834817","https://openalex.org/W1568232062","https://openalex.org/W1819710477","https://openalex.org/W1976951404","https://openalex.org/W2016430046","https://openalex.org/W2031647436","https://openalex.org/W2063224314","https://openalex.org/W2064675550","https://openalex.org/W2090681206","https://openalex.org/W2090861223","https://openalex.org/W2091828388","https://openalex.org/W2094461119","https://openalex.org/W2101045344","https://openalex.org/W2102113734","https://openalex.org/W2107878631","https://openalex.org/W2127851351","https://openalex.org/W2136848157","https://openalex.org/W2141411743","https://openalex.org/W2143612262","https://openalex.org/W2152937398","https://openalex.org/W2172097686","https://openalex.org/W2290318471","https://openalex.org/W2405589348","https://openalex.org/W2799238042","https://openalex.org/W2962968839","https://openalex.org/W6675365184","https://openalex.org/W6713519970","https://openalex.org/W6750552775"],"related_works":["https://openalex.org/W2127243424","https://openalex.org/W4390394189","https://openalex.org/W2037504162","https://openalex.org/W2792706544","https://openalex.org/W1568451138","https://openalex.org/W2539013788","https://openalex.org/W2156699640","https://openalex.org/W2045265907","https://openalex.org/W2972997031","https://openalex.org/W2075222291"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"an":[3],"in-depth":[4],"investigation":[5],"of":[6,56,100],"training":[7,29],"criteria,":[8],"network":[9],"architectures":[10],"and":[11,39,64,74],"feature":[12,49,103],"representations":[13],"for":[14,105],"regression-based":[15],"single-channel":[16],"speech":[17,44],"separation":[18,45],"with":[19],"deep":[20],"neural":[21],"networks":[22],"(DNNs).":[23],"We":[24],"use":[25],"a":[26,47],"generic":[27],"discriminative":[28,81],"criterion":[30],"corresponding":[31],"to":[32,43],"optimal":[33],"source":[34],"reconstruction":[35],"from":[36],"time-frequency":[37,57],"masks,":[38],"introduce":[40],"its":[41],"application":[42],"in":[46],"reduced":[48],"space":[50],"(Mel":[51],"domain).":[52],"A":[53],"comparative":[54],"evaluation":[55],"mask":[58],"estimation":[59],"by":[60,80],"DNNs,":[61],"recurrent":[62,87],"DNNs":[63,88],"non-negative":[65],"matrix":[66],"factorization":[67],"on":[68],"the":[69,90,98,102],"2nd":[70],"CHiME":[71],"Speech":[72],"Separation":[73],"Recognition":[75],"Challenge":[76],"shows":[77],"consistent":[78],"improvements":[79],"training,":[82],"whereas":[83],"long":[84],"short-term":[85],"memory":[86],"obtain":[89],"overall":[91],"best":[92],"results.":[93],"Furthermore,":[94],"our":[95],"results":[96],"confirm":[97],"importance":[99],"fine-tuning":[101],"representation":[104],"DNN":[106],"training.":[107]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":34},{"year":2020,"cited_by_count":48},{"year":2019,"cited_by_count":52},{"year":2018,"cited_by_count":46},{"year":2017,"cited_by_count":38},{"year":2016,"cited_by_count":17},{"year":2015,"cited_by_count":19},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}