{"id":"https://openalex.org/W3082256262","doi":"https://doi.org/10.1121/10.0001779","title":"A two-stage deep learning algorithm for talker-independent speaker separation in reverberant conditions","display_name":"A two-stage deep learning algorithm for talker-independent speaker separation in reverberant conditions","publication_year":2020,"publication_date":"2020-09-01","ids":{"openalex":"https://openalex.org/W3082256262","doi":"https://doi.org/10.1121/10.0001779","mag":"3082256262","pmid":"https://pubmed.ncbi.nlm.nih.gov/33003849","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/7473777"},"language":"en","primary_location":{"id":"doi:10.1121/10.0001779","doi":"https://doi.org/10.1121/10.0001779","is_oa":false,"landing_page_url":"https://doi.org/10.1121/10.0001779","pdf_url":null,"source":{"id":"https://openalex.org/S11296630","display_name":"The Journal of the Acoustical Society of America","issn_l":"0001-4966","issn":["0001-4966","1520-8524","1520-9024"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","jufo-3","ki-jl-1","medline","norway-2","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320226","host_organization_name":"Acoustical Society of America","host_organization_lineage":["https://openalex.org/P4310320226"],"host_organization_lineage_names":["Acoustical Society of America"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of the Acoustical Society of America","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7473777","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","observed_orcids":["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 , Columbus, Ohio 43210, USA"],"raw_orcid":"https://orcid.org/0000-0002-8354-0832","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University , Columbus, Ohio 43210, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101800003","display_name":"Yuzhou Liu","orcid":"https://orcid.org/0000-0002-7030-9121","observed_orcids":["https://orcid.org/0000-0002-7030-9121"]},"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":"Yuzhou Liu","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University , Columbus, Ohio 43210, USA"],"raw_orcid":"https://orcid.org/0000-0002-7030-9121","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University , Columbus, Ohio 43210, 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","observed_orcids":["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, The Ohio State University , Columbus, Ohio 43210, USA"],"raw_orcid":"https://orcid.org/0000-0001-8195-6319","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University , Columbus, Ohio 43210, 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":0.5419,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.65156213,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"148","issue":"3","first_page":"1157","last_page":"1168"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9336000084877014,"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":0.9336000084877014,"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":0.06109999865293503,"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":0.0038999998942017555,"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-separation","display_name":"speech separation","score":0.7570000290870667},{"id":"https://openalex.org/keywords/reverberation","display_name":"reverberation","score":0.7770000100135803},{"id":"https://openalex.org/keywords/speech-dereverberation","display_name":"speech dereverberation","score":0.9660000205039978},{"id":"https://openalex.org/keywords/computational-auditory-scene-analysis","display_name":"computational auditory scene analysis","score":0.9890000224113464},{"id":"https://openalex.org/keywords/two-stage-deep-learning","display_name":"two-stage deep learning","score":0.8569999933242798}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7364955544471741},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.720766544342041},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6980816721916199},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6238861083984375},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.5798907279968262},{"id":"https://openalex.org/C149712133","wikidata":"https://www.wikidata.org/wiki/Q332774","display_name":"Anechoic chamber","level":2,"score":0.5673664808273315},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.42587268352508545},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3878861963748932},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3529931306838989},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32628360390663147},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.28678780794143677},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11944091320037842},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.05733901262283325},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013067","descriptor_name":"Speech Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1121/10.0001779","doi":"https://doi.org/10.1121/10.0001779","is_oa":false,"landing_page_url":"https://doi.org/10.1121/10.0001779","pdf_url":null,"source":{"id":"https://openalex.org/S11296630","display_name":"The Journal of the Acoustical Society of America","issn_l":"0001-4966","issn":["0001-4966","1520-8524","1520-9024"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","jufo-3","ki-jl-1","medline","norway-2","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320226","host_organization_name":"Acoustical Society of America","host_organization_lineage":["https://openalex.org/P4310320226"],"host_organization_lineage_names":["Acoustical Society of America"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of the Acoustical Society of America","raw_type":"journal-article"},{"id":"pmh:oai:pubmedcentral.nih.gov:7473777","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7473777","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,"listed_in":[],"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":"J Acoust Soc Am","raw_type":"Text"},{"id":"pmid:33003849","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33003849","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,"listed_in":[],"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":"The Journal of the Acoustical Society of America","raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:7473777","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7473777","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,"listed_in":[],"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":"J Acoust Soc Am","raw_type":"Text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, justice, and strong institutions","score":0.4399999976158142}],"study_designs":[],"awards":[{"id":"https://openalex.org/G6572069668","display_name":"Speech segregation to improve intelligility of reverberant-noisy speech","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/F4320337352","display_name":"National Institute on Deafness and Other Communication Disorders","ror":"https://ror.org/04mhx6838"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1500640442","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1790748249","https://openalex.org/W1901129140","https://openalex.org/W1963835294","https://openalex.org/W1980459899","https://openalex.org/W1989320958","https://openalex.org/W1991112797","https://openalex.org/W2031647436","https://openalex.org/W2063669828","https://openalex.org/W2069681747","https://openalex.org/W2087368178","https://openalex.org/W2091766358","https://openalex.org/W2114218864","https://openalex.org/W2124149378","https://openalex.org/W2127851351","https://openalex.org/W2141998673","https://openalex.org/W2168379380","https://openalex.org/W2221409856","https://openalex.org/W2291877678","https://openalex.org/W2304609584","https://openalex.org/W2460742184","https://openalex.org/W2510642588","https://openalex.org/W2516001803","https://openalex.org/W2610674366","https://openalex.org/W2622055663","https://openalex.org/W2625041691","https://openalex.org/W2734774145","https://openalex.org/W2792764867","https://openalex.org/W2889384217","https://openalex.org/W2890820256","https://openalex.org/W2892163332","https://openalex.org/W2900893004","https://openalex.org/W2920977479","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2963446712","https://openalex.org/W2968723745","https://openalex.org/W2972460025","https://openalex.org/W2972853597","https://openalex.org/W3016066622","https://openalex.org/W3082256262","https://openalex.org/W4231807801"],"related_works":["https://openalex.org/W3016066622","https://openalex.org/W2968723745","https://openalex.org/W2972460025","https://openalex.org/W3041647828","https://openalex.org/W3011353161","https://openalex.org/W3015390914","https://openalex.org/W2890111732","https://openalex.org/W3036300646","https://openalex.org/W7046360508","https://openalex.org/W4387520297"],"abstract_inverted_index":{"Speaker":[0],"separation":[1,22,47,56,112],"is":[2,73],"a":[3,70,97,143],"special":[4],"case":[5],"of":[6],"speech":[7,58,136],"separation,":[8],"in":[9,27,34,48,103,121],"which":[10],"the":[11,61,115],"mixture":[12],"signal":[13],"comprises":[14],"two":[15],"or":[16],"more":[17,39],"speakers.":[18,127],"Many":[19],"talker-independent":[20,45],"speaker":[21,46,55],"methods":[23],"have":[24],"been":[25],"introduced":[26],"recent":[28],"years":[29],"to":[30,69,125,133,142],"address":[31],"this":[32,42,76],"problem":[33],"anechoic":[35],"conditions.":[36,50,106],"To":[37,51],"consider":[38],"realistic":[40],"environments,":[41],"paper":[43],"investigates":[44],"reverberant":[49,78,105],"effectively":[52],"deal":[53],"with":[54],"and":[57,83,118,138],"dereverberation,":[59],"extending":[60],"deep":[62,92,100],"computational":[63],"auditory":[64],"scene":[65],"analysis":[66],"(CASA)":[67],"approach":[68],"two-stage":[71,91],"system":[72,94,109,130],"proposed.":[74],"In":[75],"method,":[77],"utterances":[79,85],"are":[80,86],"first":[81],"separated":[82,84,123],"then":[87],"dereverberated.":[88],"The":[89,107,128],"proposed":[90,108,129],"CASA":[93,101],"significantly":[95],"outperforms":[96],"baseline":[98],"one-stage":[99],"method":[102],"real":[104],"has":[110],"superior":[111],"performance":[113,141],"at":[114],"frame":[116],"level":[117],"higher":[119],"accuracy":[120],"assigning":[122],"frames":[124],"individual":[126],"successfully":[131],"generalizes":[132],"an":[134],"unseen":[135],"corpus":[137],"exhibits":[139],"similar":[140],"talker-dependent":[144],"system.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2020-09-08T00:00:00"}