{"id":"https://openalex.org/W2968723745","doi":"https://doi.org/10.1109/taslp.2019.2934319","title":"Deep Learning for Talker-Dependent Reverberant Speaker Separation: An Empirical Study","display_name":"Deep Learning for Talker-Dependent Reverberant Speaker Separation: An Empirical Study","publication_year":2019,"publication_date":"2019-08-13","ids":{"openalex":"https://openalex.org/W2968723745","doi":"https://doi.org/10.1109/taslp.2019.2934319","mag":"2968723745","pmid":"https://pubmed.ncbi.nlm.nih.gov/33748321"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2019.2934319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2934319","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/7970708","any_repository_has_fulltext":true},"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":["Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0002-8354-0832","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, The Ohio State University, Columbus, OH, 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":["Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0001-8195-6319","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, The Ohio State University, Columbus, OH, 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":3.7629,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.94383433,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"27","issue":"11","first_page":"1839","last_page":"1848"},"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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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":0.996999979019165,"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/reverberation","display_name":"Reverberation","score":0.7569563388824463},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6947465538978577},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6832727193832397},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.6486696004867554},{"id":"https://openalex.org/keywords/anechoic-chamber","display_name":"Anechoic chamber","score":0.5418411493301392},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5203313827514648},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.4914053678512573},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4893342852592468},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.4440239369869232},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.40060874819755554},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2939119040966034},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1310490369796753},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08144000172615051},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06527242064476013}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.7569563388824463},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6947465538978577},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6832727193832397},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6486696004867554},{"id":"https://openalex.org/C149712133","wikidata":"https://www.wikidata.org/wiki/Q332774","display_name":"Anechoic chamber","level":2,"score":0.5418411493301392},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5203313827514648},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.4914053678512573},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4893342852592468},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4440239369869232},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.40060874819755554},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2939119040966034},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1310490369796753},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08144000172615051},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06527242064476013},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2019.2934319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2934319","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:33748321","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33748321","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:pubmedcentral.nih.gov:7970708","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7970708","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:7970708","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7970708","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":[{"score":0.4000000059604645,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"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"}],"funders":[{"id":"https://openalex.org/F4320317189","display_name":"Ohio Supercomputer Center","ror":"https://ror.org/01apna436"},{"id":"https://openalex.org/F4320337352","display_name":"National Institute on Deafness and Other Communication Disorders","ror":"https://ror.org/04mhx6838"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1665214252","https://openalex.org/W1790748249","https://openalex.org/W1989320958","https://openalex.org/W2004867530","https://openalex.org/W2010275911","https://openalex.org/W2020997493","https://openalex.org/W2031647436","https://openalex.org/W2046869671","https://openalex.org/W2057200980","https://openalex.org/W2057653135","https://openalex.org/W2063669828","https://openalex.org/W2064675550","https://openalex.org/W2069681747","https://openalex.org/W2087368178","https://openalex.org/W2102346872","https://openalex.org/W2114218864","https://openalex.org/W2117678320","https://openalex.org/W2127851351","https://openalex.org/W2168379380","https://openalex.org/W2221409856","https://openalex.org/W2304609584","https://openalex.org/W2326699523","https://openalex.org/W2516001803","https://openalex.org/W2558539285","https://openalex.org/W2561557072","https://openalex.org/W2598036111","https://openalex.org/W2610674366","https://openalex.org/W2622055663","https://openalex.org/W2625041691","https://openalex.org/W2734774145","https://openalex.org/W2890820256","https://openalex.org/W2891283181","https://openalex.org/W2891405874","https://openalex.org/W2892365986","https://openalex.org/W2900893004","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2964121744","https://openalex.org/W2996969697","https://openalex.org/W3099330747","https://openalex.org/W3124794156","https://openalex.org/W4231807801","https://openalex.org/W4253928870","https://openalex.org/W6631190155","https://openalex.org/W6637242042","https://openalex.org/W6675700563","https://openalex.org/W6754743415","https://openalex.org/W6759323020"],"related_works":["https://openalex.org/W2732511158","https://openalex.org/W2101177031","https://openalex.org/W4234190324","https://openalex.org/W4396668120","https://openalex.org/W2126085626","https://openalex.org/W1539630658","https://openalex.org/W36105149","https://openalex.org/W2545131480","https://openalex.org/W1973693762","https://openalex.org/W208363076"],"abstract_inverted_index":{"Speaker":[0],"separation":[1,24,37,76],"refers":[2],"to":[3,20,58,70],"the":[4,22,32,62,81,84,93,98,106],"problem":[5,25,33],"of":[6,13,34,44,130],"separating":[7],"speech":[8,64,78],"signals":[9],"from":[10],"a":[11,127],"mixture":[12],"simultaneous":[14],"speakers.":[15],"Previous":[16],"studies":[17],"are":[18,42],"limited":[19],"addressing":[21],"speaker":[23,36,75,157],"in":[26,38,126,136],"anechoic":[27],"conditions.":[28],"This":[29],"paper":[30],"addresses":[31],"talker-dependent":[35],"reverberant":[39,156],"conditions,":[40],"which":[41],"characteristic":[43],"real-world":[45],"environments.":[46],"We":[47,66,102],"employ":[48],"recurrent":[49],"neural":[50],"networks":[51,69,125],"with":[52,73],"bidirectional":[53],"long":[54],"short-term":[55],"memory":[56],"(BLSTM)":[57],"separate":[59],"and":[60,77,88,92,109,119,133],"dereverberate":[61],"target":[63,100],"signal.":[65,101],"propose":[67],"two-stage":[68,82,107],"effectively":[71],"deal":[72],"both":[74],"dereverberation.":[79],"In":[80],"model,":[83],"first":[85],"stage":[86,95],"separates":[87],"dereverberates":[89],"two-talker":[90],"mixtures":[91,118],"second":[94],"further":[96],"enhances":[97],"separated":[99],"have":[103],"extensively":[104],"evaluated":[105],"architecture,":[108],"our":[110],"empirical":[111],"results":[112],"demonstrate":[113],"large":[114],"improvements":[115],"over":[116,123],"unprocessed":[117],"clear":[120],"performance":[121,151],"gain":[122],"single-stage":[124],"wide":[128],"range":[129],"target-to-interferer":[131],"ratios":[132],"reverberation":[134],"times":[135],"simulated":[137],"as":[138,140],"well":[139],"recorded":[141],"rooms.":[142],"Moreover,":[143],"we":[144],"show":[145],"that":[146],"time-frequency":[147],"masking":[148],"yields":[149],"better":[150],"than":[152],"spectral":[153],"mapping":[154],"for":[155],"separation.":[158]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":2}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}