{"id":"https://openalex.org/W2891283181","doi":"https://doi.org/10.1109/icassp.2018.8462014","title":"Recurrent Neural Networks for Cochannel Speech Separation in Reverberant Environments","display_name":"Recurrent Neural Networks for Cochannel Speech Separation in Reverberant Environments","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2891283181","doi":"https://doi.org/10.1109/icassp.2018.8462014","mag":"2891283181"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5012541772","display_name":"Masood Delfarah","orcid":"https://orcid.org/0000-0002-8354-0832"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Masood Delfarah","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Center for Cognitive and Brain Sciences, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5404","last_page":"5408"},"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":0.9979000091552734,"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/T11309","display_name":"Music and Audio Processing","score":0.9966999888420105,"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":0.7671090364456177},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7521132230758667},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.72530198097229},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.7014748454093933},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6653232574462891},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5892337560653687},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4979860782623291},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4843965172767639},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48327189683914185},{"id":"https://openalex.org/keywords/impulse","display_name":"Impulse (physics)","score":0.47765862941741943},{"id":"https://openalex.org/keywords/feed-forward","display_name":"Feed forward","score":0.42509427666664124},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4231525659561157},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.4226810336112976},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34639620780944824},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32713425159454346},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.25540077686309814},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12826037406921387},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12016880512237549},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.089560866355896}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7671090364456177},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7521132230758667},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.72530198097229},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.7014748454093933},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6653232574462891},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5892337560653687},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4979860782623291},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4843965172767639},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48327189683914185},{"id":"https://openalex.org/C70836080","wikidata":"https://www.wikidata.org/wiki/Q837940","display_name":"Impulse (physics)","level":2,"score":0.47765862941741943},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.42509427666664124},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4231525659561157},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.4226810336112976},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34639620780944824},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32713425159454346},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.25540077686309814},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12826037406921387},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12016880512237549},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.089560866355896},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1522301498","https://openalex.org/W1790748249","https://openalex.org/W1897240248","https://openalex.org/W2006129368","https://openalex.org/W2031647436","https://openalex.org/W2043356347","https://openalex.org/W2064675550","https://openalex.org/W2069681747","https://openalex.org/W2087368178","https://openalex.org/W2091766358","https://openalex.org/W2114218864","https://openalex.org/W2114719288","https://openalex.org/W2117678320","https://openalex.org/W2125562558","https://openalex.org/W2136922672","https://openalex.org/W2144786298","https://openalex.org/W2152037357","https://openalex.org/W2164432048","https://openalex.org/W2168379380","https://openalex.org/W2221409856","https://openalex.org/W2304609584","https://openalex.org/W2326699523","https://openalex.org/W2404892923","https://openalex.org/W2558649592","https://openalex.org/W2598036111","https://openalex.org/W2635471793","https://openalex.org/W2678916739","https://openalex.org/W2734774145","https://openalex.org/W2964121744","https://openalex.org/W3124794156","https://openalex.org/W4231807801","https://openalex.org/W6631190155","https://openalex.org/W6639532686","https://openalex.org/W6684274455","https://openalex.org/W6688843265","https://openalex.org/W6713860163","https://openalex.org/W6739504299"],"related_works":["https://openalex.org/W2621851636","https://openalex.org/W2103031592","https://openalex.org/W1967226023","https://openalex.org/W1986772939","https://openalex.org/W2538939196","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W2542062716","https://openalex.org/W2955471771","https://openalex.org/W1505346162"],"abstract_inverted_index":{"Speech":[0],"separation":[1,16],"is":[2,14,87,95],"a":[3,21,25],"fundamental":[4],"problem":[5],"in":[6,24,42,48,59,101],"speech":[7,46,62,75],"and":[8,44,77],"signal":[9],"processing.":[10],"A":[11],"particular":[12],"challenge":[13],"monaural":[15],"of":[17],"cochannel":[18,50],"speech,":[19],"or":[20],"two-talker":[22],"mixture,":[23],"reverberant":[26,49,61,110],"environment.":[27],"In":[28,64],"this":[29],"paper,":[30],"we":[31],"study":[32],"recurrent":[33],"neural":[34],"networks":[35,71],"(RNNs)":[36],"with":[37,103],"long":[38],"short-term":[39],"memory":[40],"(LSTM)":[41],"separating":[43,60],"enhancing":[45],"signals":[47,111,127],"mixtures.":[51],"Our":[52],"investigation":[53],"shows":[54],"that":[55,83],"RNNs":[56,66],"are":[57,128],"effective":[58],"signals.":[63],"addition,":[65],"significantly":[67],"outperform":[68],"deep":[69],"feedforward":[70],"based":[72],"on":[73],"objective":[74],"intelligibility":[76],"quality":[78],"measures.":[79],"We":[80],"also":[81],"find":[82],"the":[84,90,98,126],"best":[85],"performance":[86],"achieved":[88],"when":[89],"ideal":[91],"ratio":[92],"mask":[93],"(IRM)":[94],"used":[96],"as":[97],"training":[99,105],"target":[100],"comparison":[102],"alternative":[104],"targets.":[106],"While":[107],"trained":[108],"using":[109],"generated":[112,129],"by":[113,130],"simulated":[114],"room":[115],"impulse":[116],"responses":[117],"(RIRs),":[118],"our":[119],"model":[120],"generalizes":[121],"well":[122],"to":[123],"conditions":[124],"where":[125],"recorded":[131],"RIRs.":[132]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}