{"id":"https://openalex.org/W2972460025","doi":"https://doi.org/10.1109/taslp.2019.2941148","title":"Divide and Conquer: A Deep CASA Approach to Talker-Independent Monaural Speaker Separation","display_name":"Divide and Conquer: A Deep CASA Approach to Talker-Independent Monaural Speaker Separation","publication_year":2019,"publication_date":"2019-09-12","ids":{"openalex":"https://openalex.org/W2972460025","doi":"https://doi.org/10.1109/taslp.2019.2941148","mag":"2972460025","pmid":"https://pubmed.ncbi.nlm.nih.gov/33748322"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2019.2941148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2941148","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/7976856","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101800003","display_name":"Yuzhou Liu","orcid":"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, OH 43210-1277 USA","Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, 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, OH 43210-1277 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"]}]},{"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 43210-1277 USA","Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0001-8195-6319","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH 43210-1277 USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, 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":17.4942,"has_fulltext":false,"cited_by_count":174,"citation_normalized_percentile":{"value":0.99524162,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"27","issue":"12","first_page":"2092","last_page":"2102"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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/monaural","display_name":"Monaural","score":0.9031042456626892},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7893950939178467},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6988598108291626},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.6164678335189819},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6011591553688049},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6008447408676147},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5981017351150513},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5307949185371399},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4991025924682617},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4881795048713684},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.46689021587371826},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42486006021499634},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.42171716690063477},{"id":"https://openalex.org/keywords/computational-auditory-scene-analysis","display_name":"Computational auditory scene analysis","score":0.414242684841156},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.2830454111099243},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2364707887172699},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.07231327891349792}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.9031042456626892},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7893950939178467},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6988598108291626},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6164678335189819},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6011591553688049},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6008447408676147},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5981017351150513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5307949185371399},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4991025924682617},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4881795048713684},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.46689021587371826},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42486006021499634},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.42171716690063477},{"id":"https://openalex.org/C73208851","wikidata":"https://www.wikidata.org/wiki/Q5157303","display_name":"Computational auditory scene analysis","level":2,"score":0.414242684841156},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2830454111099243},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2364707887172699},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.07231327891349792},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2019.2941148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2941148","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:33748322","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33748322","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:7976856","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7976856","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:7976856","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7976856","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":0.6000000238418579,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"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/G3481055361","display_name":null,"funder_award_id":"R01 DC015521","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1522301498","https://openalex.org/W1575829986","https://openalex.org/W1677182931","https://openalex.org/W1901129140","https://openalex.org/W1904365287","https://openalex.org/W1991112797","https://openalex.org/W2031647436","https://openalex.org/W2069681747","https://openalex.org/W2087368178","https://openalex.org/W2088361146","https://openalex.org/W2127851351","https://openalex.org/W2158331493","https://openalex.org/W2159202424","https://openalex.org/W2176412452","https://openalex.org/W2212703438","https://openalex.org/W2221409856","https://openalex.org/W2291877678","https://openalex.org/W2304609584","https://openalex.org/W2510642588","https://openalex.org/W2516001803","https://openalex.org/W2531409750","https://openalex.org/W2561557072","https://openalex.org/W2622055663","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2774707525","https://openalex.org/W2792764867","https://openalex.org/W2800022361","https://openalex.org/W2800664709","https://openalex.org/W2890111732","https://openalex.org/W2891405874","https://openalex.org/W2910254446","https://openalex.org/W2943554574","https://openalex.org/W2952218014","https://openalex.org/W2962686221","https://openalex.org/W2962832505","https://openalex.org/W2962905190","https://openalex.org/W2963266340","https://openalex.org/W2963285578","https://openalex.org/W2963317762","https://openalex.org/W2963446712","https://openalex.org/W2963750251","https://openalex.org/W2964121744","https://openalex.org/W2996969697","https://openalex.org/W3099330747","https://openalex.org/W3124972797","https://openalex.org/W4256399001","https://openalex.org/W4297797397","https://openalex.org/W4299838440","https://openalex.org/W6631190155","https://openalex.org/W6639824700","https://openalex.org/W6640036494","https://openalex.org/W6685562342","https://openalex.org/W6688167117","https://openalex.org/W6697814554","https://openalex.org/W6742632731","https://openalex.org/W6746914816","https://openalex.org/W6749825310","https://openalex.org/W6759323020","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1974981856","https://openalex.org/W1518859147","https://openalex.org/W2045506488","https://openalex.org/W2550493152","https://openalex.org/W1653463454","https://openalex.org/W2078587651","https://openalex.org/W3145694760","https://openalex.org/W2935873029"],"abstract_inverted_index":{"We":[0],"address":[1],"talker-independent":[2],"monaural":[3],"speaker":[4,83],"separation":[5,23,81],"from":[6],"the":[7,21,26,45,57,60,97,103,107],"perspectives":[8],"of":[9,28,47],"deep":[10,76],"learning":[11],"and":[12,31,82,87],"computational":[13],"auditory":[14],"scene":[15],"analysis":[16],"(CASA).":[17],"Specifically,":[18],"we":[19],"decompose":[20],"multi-speaker":[22],"task":[24],"into":[25],"stages":[27],"simultaneous":[29],"grouping":[30,35],"sequential":[32],"grouping.":[33],"Simultaneous":[34],"is":[36],"first":[37],"performed":[38],"in":[39,85],"each":[40],"time":[41],"frame":[42],"by":[43,70],"separating":[44],"spectra":[46,63],"different":[48,68],"speakers":[49,69],"with":[50,110],"a":[51,71,111],"permutation-invariantly":[52],"trained":[53],"neural":[54],"network.":[55,73],"In":[56],"second":[58],"stage,":[59],"frame-level":[61,80],"separated":[62],"are":[64],"sequentially":[65],"grouped":[66],"to":[67],"clustering":[72],"The":[74],"proposed":[75],"CASA":[77],"approach":[78,105],"optimizes":[79],"tracking":[84],"turn,":[86],"produces":[88],"excellent":[89],"results":[90,95,109],"for":[91],"both":[92],"objectives.":[93],"Experimental":[94],"on":[96],"benchmark":[98],"WSJ0-2mix":[99],"database":[100],"show":[101],"that":[102],"new":[104],"achieves":[106],"state-of-the-art":[108],"modest":[112],"model":[113],"size.":[114]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":28},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":45},{"year":2020,"cited_by_count":38},{"year":2019,"cited_by_count":4}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
