{"id":"https://openalex.org/W160800111","doi":"https://doi.org/10.1007/0-387-22794-6_12","title":"On Ideal Binary Mask As the Computational Goal of Auditory Scene Analysis","display_name":"On Ideal Binary Mask As the Computational Goal of Auditory Scene Analysis","publication_year":2006,"publication_date":"2006-01-10","ids":{"openalex":"https://openalex.org/W160800111","doi":"https://doi.org/10.1007/0-387-22794-6_12","mag":"160800111"},"language":"en","primary_location":{"id":"doi:10.1007/0-387-22794-6_12","doi":"https://doi.org/10.1007/0-387-22794-6_12","is_oa":false,"landing_page_url":"https://doi.org/10.1007/0-387-22794-6_12","pdf_url":null,"source":{"id":"https://openalex.org/S4306463519","display_name":"Kluwer Academic Publishers eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"ebook platform"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Speech Separation by Humans and Machines","raw_type":"book-chapter"},"volume":{"id":"https://openalex.org/W1500640442","display_name":"Speech Separation by Humans and Machines"},"type":"book-chapter","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/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":true,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Department of Computer Science and Engineering and Center of Cognitive Science, The Ohio State University, Columbus, OH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering and Center of Cognitive Science, The Ohio State University, Columbus, OH","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5051837453"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":61.3684,"has_fulltext":false,"cited_by_count":565,"citation_normalized_percentile":{"value":1.0,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"181","last_page":"197"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9916999936103821,"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":0.9916999936103821,"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":0.006200000178068876,"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":0.0006000000284984708,"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/auditory-scene-analysis","display_name":"auditory scene analysis","score":0.9750000238418579},{"id":"https://openalex.org/keywords/ideal-binary-mask","display_name":"ideal binary mask","score":0.9769999980926514},{"id":"https://openalex.org/keywords/theory-of-computation","display_name":"theory of computation","score":0.6240000128746033},{"id":"https://openalex.org/keywords/marr-s-levels-of-analysis","display_name":"Marr's levels of analysis","score":0.8740000128746033},{"id":"https://openalex.org/keywords/speech-separation","display_name":"speech separation","score":0.8450000286102295},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"speech enhancement","score":0.5789999961853027},{"id":"https://openalex.org/keywords/speech-intelligibility","display_name":"speech intelligibility","score":0.828000009059906},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.9110000133514404},{"id":"https://openalex.org/keywords/evaluation-indicators","display_name":"evaluation metrics","score":0.6389999985694885},{"id":"https://openalex.org/keywords/human-auditory-perception","display_name":"human auditory perception","score":0.5479999780654907}],"concepts":[{"id":"https://openalex.org/C73208851","wikidata":"https://www.wikidata.org/wiki/Q5157303","display_name":"Computational auditory scene analysis","level":2,"score":0.7398988008499146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6895912885665894},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.6808415055274963},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.6172530651092529},{"id":"https://openalex.org/C38129911","wikidata":"https://www.wikidata.org/wiki/Q4820038","display_name":"Auditory scene analysis","level":3,"score":0.5229395627975464},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5206524729728699},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.4896543622016907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37762606143951416},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3397110104560852},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.331828773021698},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.28466981649398804},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.18435299396514893},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18433237075805664},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09150201082229614},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/0-387-22794-6_12","doi":"https://doi.org/10.1007/0-387-22794-6_12","is_oa":false,"landing_page_url":"https://doi.org/10.1007/0-387-22794-6_12","pdf_url":null,"source":{"id":"https://openalex.org/S4306463519","display_name":"Kluwer Academic Publishers eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"ebook platform"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Speech Separation by Humans and Machines","raw_type":"book-chapter"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.304.7280","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.304.7280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ohio-state.edu/~dwang/papers/Wang05.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.84.298","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.84.298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ohio-state.edu/~dwang/papers/Wang05.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W72901977","https://openalex.org/W91901064","https://openalex.org/W607700452","https://openalex.org/W1500640442","https://openalex.org/W1509290216","https://openalex.org/W1510095622","https://openalex.org/W1548802052","https://openalex.org/W1567997379","https://openalex.org/W1575829986","https://openalex.org/W1956364622","https://openalex.org/W1969529608","https://openalex.org/W1979493366","https://openalex.org/W1991139021","https://openalex.org/W1998530097","https://openalex.org/W2013020033","https://openalex.org/W2019921249","https://openalex.org/W2033174849","https://openalex.org/W2034040413","https://openalex.org/W2039170454","https://openalex.org/W2044222806","https://openalex.org/W2045660721","https://openalex.org/W2046059186","https://openalex.org/W2048359125","https://openalex.org/W2060108923","https://openalex.org/W2074354966","https://openalex.org/W2080680098","https://openalex.org/W2097191389","https://openalex.org/W2110678343","https://openalex.org/W2122994683","https://openalex.org/W2127088487","https://openalex.org/W2130788908","https://openalex.org/W2145362370","https://openalex.org/W2147174722","https://openalex.org/W2149425615","https://openalex.org/W2154392779","https://openalex.org/W2162654459","https://openalex.org/W2166667242","https://openalex.org/W2168793898","https://openalex.org/W2295986502","https://openalex.org/W2612413169","https://openalex.org/W2613433911","https://openalex.org/W2970583947","https://openalex.org/W3132960064","https://openalex.org/W4205778870","https://openalex.org/W4256399001","https://openalex.org/W4310638450","https://openalex.org/W6600730691"],"related_works":["https://openalex.org/W190004713","https://openalex.org/W2006910250","https://openalex.org/W2535984625","https://openalex.org/W2895188252","https://openalex.org/W2085191029","https://openalex.org/W2281310777","https://openalex.org/W2368038768","https://openalex.org/W133022121","https://openalex.org/W2615189788","https://openalex.org/W2343541345"],"abstract_inverted_index":{"In":[0,26],"his":[1],"famous":[2],"treatise":[3],"of":[4,17,36,52,65,78,88,97,105,133,150],"computational":[5,29],"vision,":[6],"Marr":[7],"(1982)":[8],"makes":[9],"a":[10,62,94],"compelling":[11],"argument":[12],"for":[13,159],"separating":[14],"different":[15],"levels":[16],"analysis":[18,64,83],"in":[19,85],"order":[20],"to":[21,74,140,157,165],"understand":[22,75],"complex":[23],"information":[24],"processing.":[25],"particular,":[27],"the":[28,34,46,50,70,76,79,86,89,131,143,151],"theory":[30],"level,":[31,48],"concerned":[32],"with":[33,103,115],"goal":[35,96,100,111,149],"computation":[37],"and":[38,123,135,137],"general":[39],"processing":[40],"strategy,":[41],"must":[42],"be":[43],"separated":[44],"from":[45,54],"algorithm":[47],"or":[49],"separation":[51,161],"what":[53],"how.":[55],"This":[56,99],"chapter":[57],"is":[58,73,101,112,138,146],"an":[59],"attempt":[60,164],"at":[61],"computational-theory":[63],"auditory":[66,107],"scene":[67,108],"analysis,":[68],"where":[69],"main":[71,95],"task":[72],"character":[77],"CASA":[80],"problem.":[81],"My":[82],"results":[84],"proposal":[87],"ideal":[90,152],"binary":[91,153],"mask":[92,154],"as":[93,120],"CASA.":[98],"consistent":[102,114],"characteristics":[104],"human":[106],"analysis.":[109],"The":[110,126,148],"also":[113],"more":[116],"specific":[117],"objectives":[118],"such":[119,168],"enhancing":[121],"ASR":[122],"speech":[124,160],"intelligibility.":[125],"resulting":[127],"evaluation":[128],"metric":[129],"has":[130,155],"properties":[132],"simplicity":[134],"generality,":[136],"easy":[139],"apply":[141],"when":[142],"premixing":[144],"target":[145],"available.":[147],"led":[156],"effective":[158],"algorithms":[162],"that":[163],"explicitly":[166],"estimate":[167],"masks.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":36},{"year":2022,"cited_by_count":34},{"year":2021,"cited_by_count":27},{"year":2020,"cited_by_count":33},{"year":2019,"cited_by_count":36},{"year":2018,"cited_by_count":31},{"year":2017,"cited_by_count":27},{"year":2016,"cited_by_count":45},{"year":2015,"cited_by_count":30},{"year":2014,"cited_by_count":34},{"year":2013,"cited_by_count":31},{"year":2012,"cited_by_count":35}],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2016-06-24T00:00:00"}
