{"id":"https://openalex.org/W3015390914","doi":"https://doi.org/10.1109/icassp40776.2020.9054572","title":"Deep Casa for Talker-independent Monaural Speech Separation","display_name":"Deep Casa for Talker-independent Monaural Speech Separation","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015390914","doi":"https://doi.org/10.1109/icassp40776.2020.9054572","mag":"3015390914"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054572","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054572","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/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":true,"raw_author_name":"Yuzhou Liu","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","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"],"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":["Department of Computer Science and Engineering, The Ohio State University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101800003"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":2.273,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.88584595,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6354","last_page":"6358"},"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":0.9987000226974487,"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":0.9983000159263611,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.9020338654518127},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7357078194618225},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7209616303443909},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6083418726921082},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.60538649559021},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.585339367389679},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5474647879600525},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5264041423797607},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.5126416087150574},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5073193907737732},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.49360334873199463},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4687125086784363},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4659282863140106},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.46193185448646545},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.457495778799057},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4117535948753357},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3713821768760681},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11231118440628052},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10843732953071594},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09339657425880432}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.9020338654518127},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7357078194618225},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7209616303443909},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6083418726921082},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.60538649559021},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.585339367389679},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5474647879600525},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5264041423797607},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.5126416087150574},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5073193907737732},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.49360334873199463},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4687125086784363},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4659282863140106},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.46193185448646545},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.457495778799057},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4117535948753357},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3713821768760681},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11231118440628052},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10843732953071594},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09339657425880432},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054572","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054572","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.699999988079071,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1991139021","https://openalex.org/W2031647436","https://openalex.org/W2069681747","https://openalex.org/W2087368178","https://openalex.org/W2127851351","https://openalex.org/W2153331367","https://openalex.org/W2168379380","https://openalex.org/W2221409856","https://openalex.org/W2291877678","https://openalex.org/W2304609584","https://openalex.org/W2364134690","https://openalex.org/W2516001803","https://openalex.org/W2559260703","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2890111732","https://openalex.org/W2943554574","https://openalex.org/W2952218014","https://openalex.org/W2962728945","https://openalex.org/W2962866211","https://openalex.org/W2962935966","https://openalex.org/W2963317762","https://openalex.org/W2963453742","https://openalex.org/W2972460025","https://openalex.org/W2972541922","https://openalex.org/W3099330747","https://openalex.org/W3124972797","https://openalex.org/W6688843265","https://openalex.org/W6730321509"],"related_works":["https://openalex.org/W2103031592","https://openalex.org/W1967226023","https://openalex.org/W2538939196","https://openalex.org/W2955471771","https://openalex.org/W2135485548","https://openalex.org/W2002243964","https://openalex.org/W2022538999","https://openalex.org/W3090086172","https://openalex.org/W1955763106","https://openalex.org/W1585241115"],"abstract_inverted_index":{"Monaural":[0],"speech":[1,9,26,50,80],"separation":[2,57,105],"is":[3,85],"the":[4],"task":[5],"of":[6,36],"separating":[7],"target":[8],"from":[10],"interference":[11],"in":[12,22,58,60,123],"single-channel":[13],"recordings.":[14],"Although":[15],"substantial":[16,112],"progress":[17],"has":[18],"been":[19],"made":[20],"recently":[21,67],"deep":[23,69,88],"learning":[24],"based":[25],"separation,":[27],"previous":[28],"studies":[29],"usually":[30],"focus":[31],"on":[32,100],"a":[33,61,66,82,91,101],"single":[34],"type":[35],"interference,":[37,53],"either":[38],"background":[39],"noise":[40,117],"or":[41],"competing":[42],"speakers.":[43],"In":[44],"this":[45],"study,":[46],"we":[47],"address":[48],"both":[49],"and":[51,119],"nonspeech":[52],"i.e.,":[54],"monaural":[55],"speaker":[56,76],"noise,":[59],"talker-independent":[62],"fashion.":[63],"We":[64],"extend":[65],"proposed":[68,95],"CASA":[70,89],"system":[71],"to":[72,87,111],"deal":[73],"with":[74],"noisy":[75,103],"mixtures.":[77],"To":[78],"facilitate":[79],"enhancement,":[81],"denoising":[83,108],"module":[84,109],"added":[86],"as":[90],"front-end":[92],"processor.":[93],"The":[94,107],"systems":[96],"achieve":[97],"state-of-the-art":[98],"results":[99],"benchmark":[102],"two-speaker":[104],"dataset.":[106],"leads":[110],"performance":[113],"gain":[114],"across":[115],"various":[116],"types,":[118],"even":[120],"better":[121],"generalization":[122],"noise-free":[124],"conditions.":[125]},"counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}