{"id":"https://openalex.org/W2890111732","doi":"https://doi.org/10.1109/icassp.2018.8461477","title":"A Casa Approach to Deep Learning Based Speaker-Independent Co-Channel Speech Separation","display_name":"A Casa Approach to Deep Learning Based Speaker-Independent Co-Channel Speech Separation","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2890111732","doi":"https://doi.org/10.1109/icassp.2018.8461477","mag":"2890111732"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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":false,"raw_author_name":"Yuzhou Liu","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, USA"],"raw_orcid":null,"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":["Center for Cognitive and Brain Sciences, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, 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":null,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5399","last_page":"5403"},"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":0.9994000196456909,"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":0.9988999962806702,"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/computer-science","display_name":"Computer science","score":0.7471200823783875},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7200925350189209},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7036775350570679},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.6805915236473083},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6137141585350037},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5857337117195129},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5509313344955444},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4819743037223816},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.48107147216796875},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4561223089694977},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.45590701699256897},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.45334717631340027},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4451856017112732},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4420281648635864},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43975675106048584},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.42834898829460144},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2227068841457367},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2166098654270172},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12126490473747253}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7471200823783875},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7200925350189209},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7036775350570679},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.6805915236473083},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6137141585350037},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5857337117195129},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5509313344955444},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4819743037223816},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.48107147216796875},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4561223089694977},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.45590701699256897},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.45334717631340027},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4451856017112732},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4420281648635864},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43975675106048584},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.42834898829460144},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2227068841457367},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2166098654270172},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12126490473747253},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W185399533","https://openalex.org/W1482149378","https://openalex.org/W1522301498","https://openalex.org/W1575829986","https://openalex.org/W1904365287","https://openalex.org/W2031647436","https://openalex.org/W2087368178","https://openalex.org/W2088361146","https://openalex.org/W2127851351","https://openalex.org/W2149648698","https://openalex.org/W2156387975","https://openalex.org/W2159202424","https://openalex.org/W2212703438","https://openalex.org/W2221409856","https://openalex.org/W2304609584","https://openalex.org/W2558649592","https://openalex.org/W2622055663","https://openalex.org/W2734774145","https://openalex.org/W2962715207","https://openalex.org/W2963266340","https://openalex.org/W2964121744","https://openalex.org/W4256399001","https://openalex.org/W6607486085","https://openalex.org/W6631190155","https://openalex.org/W6640036494","https://openalex.org/W6672470634","https://openalex.org/W6682889407","https://openalex.org/W6688167117","https://openalex.org/W6688843265","https://openalex.org/W6730148858"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2696990509"],"abstract_inverted_index":{"We":[0],"address":[1],"speaker-independent":[2],"co-channel":[3],"speech":[4],"separation":[5,20],"from":[6],"the":[7,18,23,37,42,56,59,70,73,89,114,119],"computational":[8],"auditory":[9],"scene":[10],"analysis":[11],"(CAS":[12],"A)":[13],"perspective.":[14],"Specifically,":[15],"we":[16],"decompose":[17],"two-speaker":[19],"task":[21],"into":[22,69],"stages":[24],"of":[25,44,72,98,123],"simultaneous":[26],"grouping":[27,32],"and":[28,103,125],"sequential":[29],"grouping.":[30],"Simultaneous":[31],"is":[33,83],"first":[34],"performed":[35,85],"at":[36,63],"frame":[38,65],"level":[39],"by":[40,77],"separating":[41],"spectra":[43,62],"two":[45,74],"speakers":[46,76],"with":[47],"a":[48,78],"permutation-invariantly":[49],"trained":[50],"recurrent":[51],"neural":[52],"network":[53],"(RNN).":[54],"In":[55],"second":[57],"stage,":[58],"simultaneously":[60],"separated":[61],"each":[64],"are":[66],"sequentially":[67],"grouped":[68],"utterances":[71],"underlying":[75],"clustering":[79,105],"RNN.":[80],"Overall":[81],"optimization":[82],"then":[84],"to":[86],"fine":[87],"tune":[88],"two-stage":[90],"system.":[91],"The":[92],"proposed":[93,115],"CASA":[94],"approach":[95],"takes":[96],"advantage":[97],"permutation":[99],"invariant":[100],"training":[101],"(PIT)":[102],"deep":[104],"(DC),":[106],"but":[107],"overcomes":[108],"their":[109],"shortcomings.":[110],"Experiments":[111],"show":[112],"that":[113],"system":[116],"improves":[117],"over":[118],"best":[120],"reported":[121],"results":[122],"PIT":[124],"DC.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}