{"id":"https://openalex.org/W2094461119","doi":"https://doi.org/10.1109/icassp.2014.6854294","title":"Single-channel speech separation with memory-enhanced recurrent neural networks","display_name":"Single-channel speech separation with memory-enhanced recurrent neural networks","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2094461119","doi":"https://doi.org/10.1109/icassp.2014.6854294","mag":"2094461119"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854294","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/A5016747567","display_name":"Felix Weninger","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094487","display_name":"Intel (Germany)","ror":"https://ror.org/00m2x0g47","country_code":"DE","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210094487"]},{"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, Technische Universit\u00e4t M\u00fcnchen, Germany","Machine Intell. & Signal Process. Group, Tech. Univ. Munchen, Mu\u0308nchen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Intelligence & Signal Processing Group, Technische Universit\u00e4t M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Machine Intell. & Signal Process. Group, Tech. Univ. Munchen, Mu\u0308nchen, Germany","institution_ids":["https://openalex.org/I4210094487","https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023264395","display_name":"Florian Eyben","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094487","display_name":"Intel (Germany)","ror":"https://ror.org/00m2x0g47","country_code":"DE","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210094487"]},{"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":"Florian Eyben","raw_affiliation_strings":["Machine Intelligence & Signal Processing Group, Technische Universit\u00e4t M\u00fcnchen, Germany","Machine Intell. & Signal Process. Group, Tech. Univ. Munchen, Mu\u0308nchen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Intelligence & Signal Processing Group, Technische Universit\u00e4t M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Machine Intell. & Signal Process. Group, Tech. Univ. Munchen, Mu\u0308nchen, Germany","institution_ids":["https://openalex.org/I4210094487","https://openalex.org/I62916508"]}]},{"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/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]},{"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","GB"],"is_corresponding":false,"raw_author_name":"Bjorn Schuller","raw_affiliation_strings":["Machine Intelligence & Signal Processing Group, Technische Universit\u00e4t M\u00fcnchen, Germany","Dept. of Comput., Imperial Coll. London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Intelligence & Signal Processing Group, Technische Universit\u00e4t M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Dept. of Comput., Imperial Coll. London, London, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":129,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3709","last_page":"3713"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9970999956130981,"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/speech-recognition","display_name":"Speech recognition","score":0.7591366767883301},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7510001063346863},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5935215950012207},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5645732879638672},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5573486685752869},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5432785749435425},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.47818830609321594},{"id":"https://openalex.org/keywords/colors-of-noise","display_name":"Colors of noise","score":0.4559917151927948},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.4546436071395874},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.43777748942375183},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4354717433452606},{"id":"https://openalex.org/keywords/impulse","display_name":"Impulse (physics)","score":0.43069911003112793},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.424790620803833},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4138838052749634},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3905586898326874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.379506379365921},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1333388388156891},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10551443696022034},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08781221508979797},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.07450464367866516},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.07088160514831543}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7591366767883301},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7510001063346863},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5935215950012207},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5645732879638672},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5573486685752869},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5432785749435425},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.47818830609321594},{"id":"https://openalex.org/C114996537","wikidata":"https://www.wikidata.org/wiki/Q4854529","display_name":"Colors of noise","level":3,"score":0.4559917151927948},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.4546436071395874},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.43777748942375183},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4354717433452606},{"id":"https://openalex.org/C70836080","wikidata":"https://www.wikidata.org/wiki/Q837940","display_name":"Impulse (physics)","level":2,"score":0.43069911003112793},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.424790620803833},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4138838052749634},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3905586898326874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.379506379365921},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1333388388156891},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10551443696022034},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08781221508979797},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.07450464367866516},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.07088160514831543},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2014.6854294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854294","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:uni-augsburg.opus-bayern.de:72579","is_oa":false,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-725798","pdf_url":null,"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":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W147964346","https://openalex.org/W1999454387","https://openalex.org/W2025768430","https://openalex.org/W2032382719","https://openalex.org/W2046282162","https://openalex.org/W2053023379","https://openalex.org/W2096789154","https://openalex.org/W2110120390","https://openalex.org/W2115055618","https://openalex.org/W2115109087","https://openalex.org/W2127851351","https://openalex.org/W2131408671","https://openalex.org/W2136682440","https://openalex.org/W2136848157","https://openalex.org/W2141411743","https://openalex.org/W2143612262","https://openalex.org/W2144499799","https://openalex.org/W2152937398","https://openalex.org/W2155531311","https://openalex.org/W2158336491","https://openalex.org/W2394573230","https://openalex.org/W2396130155","https://openalex.org/W2405774341","https://openalex.org/W2747655461","https://openalex.org/W2748434850","https://openalex.org/W6712025336","https://openalex.org/W6712634873","https://openalex.org/W6713658392","https://openalex.org/W6742785727","https://openalex.org/W6743078993"],"related_works":["https://openalex.org/W2027483212","https://openalex.org/W1988207391","https://openalex.org/W2128349358","https://openalex.org/W2117625637","https://openalex.org/W2114024039","https://openalex.org/W2144910625","https://openalex.org/W1571800558","https://openalex.org/W2002243964","https://openalex.org/W2736268759","https://openalex.org/W2022538999"],"abstract_inverted_index":{"In":[0,88],"this":[1],"paper":[2],"we":[3],"propose":[4],"the":[5,56,82,89,91],"use":[6],"of":[7,60,69,127],"Long":[8],"Short-Term":[9],"Memory":[10],"recurrent":[11],"neural":[12],"networks":[13],"for":[14],"speech":[15,23,31],"enhancement.":[16],"Networks":[17],"are":[18,46],"trained":[19],"to":[20,96],"predict":[21],"clean":[22],"as":[24,26],"well":[25],"noise":[27,71,80,99],"features":[28],"from":[29,41,55,81],"noisy":[30,51],"features,":[32],"and":[33,52,75,78],"a":[34,122],"magnitude":[35,117],"domain":[36,118],"soft":[37],"mask":[38],"is":[39,94],"constructed":[40],"these":[42],"features.":[43],"Extensive":[44],"tests":[45],"run":[47],"on":[48],"73":[49],"k":[50],"reverberated":[53],"utterances":[54],"Audio-Visual":[57],"Interest":[58],"Corpus":[59],"spontaneous,":[61],"emotionally":[62],"colored":[63],"speech,":[64],"degraded":[65],"by":[66,121],"several":[67],"hours":[68],"real":[70],"recordings":[72],"comprising":[73],"stationary":[74],"non-stationary":[76],"sources":[77],"convolutive":[79],"Aachen":[83],"Room":[84],"Impulse":[85],"Response":[86],"database.":[87],"result,":[90],"proposed":[92],"method":[93],"shown":[95],"provide":[97],"superior":[98],"reduction":[100],"at":[101,110],"low":[102],"signal-to-noise":[103,112],"ratios":[104],"while":[105],"creating":[106],"very":[107],"little":[108],"artifacts":[109],"higher":[111],"ratios,":[113],"thereby":[114],"outperforming":[115],"unsupervised":[116],"spectral":[119],"subtraction":[120],"large":[123],"margin":[124],"in":[125],"terms":[126],"source-distortion":[128],"ratio.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":17},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}