{"id":"https://openalex.org/W2599685671","doi":"https://doi.org/10.1109/taslp.2017.2687104","title":"Deep Learning Based Binaural Speech Separation in Reverberant Environments","display_name":"Deep Learning Based Binaural Speech Separation in Reverberant Environments","publication_year":2017,"publication_date":"2017-03-25","ids":{"openalex":"https://openalex.org/W2599685671","doi":"https://doi.org/10.1109/taslp.2017.2687104","mag":"2599685671","pmid":"https://pubmed.ncbi.nlm.nih.gov/29057291"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2017.2687104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2687104","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":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5646682","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100693230","display_name":"Xueliang Zhang","orcid":"https://orcid.org/0000-0002-0406-1105"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueliang Zhang","raw_affiliation_strings":["Department of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"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":["Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH 43202 USA","Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH 43202 USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.6913,"has_fulltext":false,"cited_by_count":119,"citation_normalized_percentile":{"value":0.99074663,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"25","issue":"5","first_page":"1075","last_page":"1084"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9968000054359436,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.9010390043258667},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.8080989122390747},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7100441455841064},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6498917937278748},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5596520304679871},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5552778840065002},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5410515069961548},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5035378336906433},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45752274990081787},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4563276767730713},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.4536052644252777},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4496956467628479},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2642298638820648},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.18030515313148499}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.9010390043258667},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.8080989122390747},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7100441455841064},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6498917937278748},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5596520304679871},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5552778840065002},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5410515069961548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5035378336906433},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45752274990081787},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4563276767730713},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.4536052644252777},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4496956467628479},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2642298638820648},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.18030515313148499},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/taslp.2017.2687104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2687104","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":"pmid:29057291","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29057291","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"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":null},{"id":"pmh:oai:europepmc.org:4846916","is_oa":false,"landing_page_url":"http://europepmc.org/pmc/articles/PMC5646682","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:5646682","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5646682","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Trans Audio Speech Lang Process","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:5646682","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5646682","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Trans Audio Speech Lang Process","raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2910152985","display_name":null,"funder_award_id":"R01 DC012048","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"},{"id":"https://openalex.org/G4332130492","display_name":null,"funder_award_id":"R01DC012048","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"},{"id":"https://openalex.org/G8822322065","display_name":null,"funder_award_id":"FA9550-12-1-0130","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G965137926","display_name":"\u8ba1\u7b97\u542c\u89c9\u573a\u666f\u5206\u6790\u4e2d\u57fa\u4e8e\u7edf\u8ba1\u6a21\u578b\u7684\u542c\u89c9\u7247\u6bb5\u5207\u5206\u7814\u7a76","funder_award_id":"61365006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320308276","display_name":"Ohio State University Press","ror":"https://ror.org/00rs6vg23"},{"id":"https://openalex.org/F4320309374","display_name":"Ohio State University","ror":"https://ror.org/00rs6vg23"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337352","display_name":"National Institute on Deafness and Other Communication Disorders","ror":"https://ror.org/04mhx6838"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W1495679096","https://openalex.org/W1515932869","https://openalex.org/W1522301498","https://openalex.org/W1575829986","https://openalex.org/W1665214252","https://openalex.org/W1677182931","https://openalex.org/W1790748249","https://openalex.org/W1963970749","https://openalex.org/W1987906574","https://openalex.org/W1989364685","https://openalex.org/W1992879732","https://openalex.org/W2034040413","https://openalex.org/W2046317813","https://openalex.org/W2046869671","https://openalex.org/W2054150774","https://openalex.org/W2057200980","https://openalex.org/W2060108923","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2095705004","https://openalex.org/W2096439661","https://openalex.org/W2101609516","https://openalex.org/W2121141823","https://openalex.org/W2129171989","https://openalex.org/W2141998673","https://openalex.org/W2144244295","https://openalex.org/W2146502635","https://openalex.org/W2165899180","https://openalex.org/W2168379380","https://openalex.org/W2168729028","https://openalex.org/W2344535577","https://openalex.org/W2364134690","https://openalex.org/W2405404760","https://openalex.org/W2532854561","https://openalex.org/W2963285578","https://openalex.org/W2964121744","https://openalex.org/W3124794156","https://openalex.org/W3127686677","https://openalex.org/W4231807801","https://openalex.org/W4233392025","https://openalex.org/W4245919820","https://openalex.org/W4249052411","https://openalex.org/W4256399001","https://openalex.org/W6637242042","https://openalex.org/W6674330103","https://openalex.org/W6681435938","https://openalex.org/W6685562342","https://openalex.org/W6713369370"],"related_works":["https://openalex.org/W2766995619","https://openalex.org/W1656519308","https://openalex.org/W4224270619","https://openalex.org/W2042717753","https://openalex.org/W2579722767","https://openalex.org/W2022849831","https://openalex.org/W2037265366","https://openalex.org/W2391832549","https://openalex.org/W1982169876","https://openalex.org/W2077498359"],"abstract_inverted_index":{"Speech":[0],"signal":[1,21],"is":[2,30,73,85],"usually":[3],"degraded":[4],"by":[5],"room":[6],"reverberation":[7],"and":[8,37,47,63,75,94,106,114],"additive":[9],"noises":[10],"in":[11,22],"real":[12],"environments.":[13,116],"This":[14],"paper":[15],"focuses":[16],"on":[17],"separating":[18],"target":[19,84],"speech":[20],"reverberant":[23,115],"conditions":[24],"from":[25,44],"binaural":[26,55],"inputs.":[27],"Binaural":[28],"separation":[29,104],"formulated":[31],"as":[32],"a":[33,51,60],"supervised":[34],"learning":[35,41],"problem,":[36],"we":[38,57],"employ":[39],"deep":[40],"to":[42,50,77],"map":[43],"both":[45],"spatial":[46,71],"spectral":[48,67,80],"features":[49],"training":[52,83],"target.":[53],"With":[54],"inputs,":[56],"first":[58],"apply":[59],"fixed":[61],"beamformer":[62],"then":[64],"extract":[65],"several":[66],"features.":[68,81],"A":[69],"new":[70],"feature":[72],"proposed":[74,99],"extracted":[76],"complement":[78],"the":[79,86,98],"The":[82],"recently":[87],"suggested":[88],"ideal":[89],"ratio":[90],"mask.":[91],"Systematic":[92],"evaluations":[93],"comparisons":[95],"show":[96],"that":[97],"system":[100],"achieves":[101],"very":[102],"good":[103],"performance":[105],"substantially":[107],"outperforms":[108],"related":[109],"algorithms":[110],"under":[111],"challenging":[112],"multi-source":[113]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":24},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":18},{"year":2017,"cited_by_count":5}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}
