{"id":"https://openalex.org/W2120076267","doi":"https://doi.org/10.1109/icassp.2004.1326272","title":"Binaural sound segregation for multisource reverberant environments","display_name":"Binaural sound segregation for multisource reverberant environments","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2120076267","doi":"https://doi.org/10.1109/icassp.2004.1326272","mag":"2120076267"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326272","doi":"https://doi.org/10.1109/icassp.2004.1326272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326272","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},"volume":null,"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/A5053306339","display_name":"Nicoleta Roman","orcid":"https://orcid.org/0000-0001-9626-6329","observed_orcids":["https://orcid.org/0000-0001-9626-6329"]},"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":"N. Roman","raw_affiliation_strings":["Department of Computer and Information, Science and Center for Cognitive Sciece, Ohio State Uinversity, Columbus, OH, USA","Dept of Comput. & Inf. Sci., Ohio State Univ., Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information, Science and Center for Cognitive Sciece, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Dept of Comput. & Inf. Sci., Ohio State Univ., 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","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 and Information, Science and Center for Cognitive Sciece, Ohio State Uinversity, Columbus, OH, USA","Dept of Comput. & Inf. Sci., Ohio State Univ., Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information, Science and Center for Cognitive Sciece, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Dept of Comput. & Inf. Sci., Ohio State Univ., 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":3.8036,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.94588649,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"2","issue":null,"first_page":"ii","last_page":"373"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9961000084877014,"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":0.9961000084877014,"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":0.0019000000320374966,"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":0.0012000000569969416,"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/adaptive-filtering","display_name":"adaptive filtering","score":0.6299999952316284},{"id":"https://openalex.org/keywords/interference-suppression","display_name":"interference suppression","score":0.5929999947547913},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.7649999856948853}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.8242397308349609},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.7942732572555542},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6621330380439758},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6571335196495056},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.6497570276260376},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.586932361125946},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.5677784085273743},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5561347603797913},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.5406962633132935},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5007469654083252},{"id":"https://openalex.org/C102248274","wikidata":"https://www.wikidata.org/wiki/Q168388","display_name":"Adaptive filter","level":2,"score":0.44765058159828186},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2249731719493866},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.18100404739379883},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17772597074508667},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1682252287864685},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15970736742019653},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0983060896396637},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2004.1326272","doi":"https://doi.org/10.1109/icassp.2004.1326272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326272","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.129.3567","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.129.3567","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/Roman-Wang.icassp04.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.5899999737739563,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W287108988","https://openalex.org/W1492221128","https://openalex.org/W1519903322","https://openalex.org/W1544582875","https://openalex.org/W1956364622","https://openalex.org/W2034040413","https://openalex.org/W2074354966","https://openalex.org/W2088805357","https://openalex.org/W2096554907","https://openalex.org/W2106325442","https://openalex.org/W2122994683","https://openalex.org/W2603761070"],"related_works":["https://openalex.org/W2057662515","https://openalex.org/W2112773389","https://openalex.org/W2034763797","https://openalex.org/W1681324445","https://openalex.org/W2034040413","https://openalex.org/W155806678","https://openalex.org/W2111890897","https://openalex.org/W2113107769","https://openalex.org/W2110460752","https://openalex.org/W7097402640"],"abstract_inverted_index":{"We":[0,19],"present":[1],"a":[2,41,73],"novel":[3],"method":[4],"for":[5],"binaural":[6],"sound":[7],"segregation":[8],"from":[9],"acoustic":[10],"mixtures":[11],"contaminated":[12],"by":[13,72,90],"both":[14],"multiple":[15],"interference":[16,39],"and":[17],"reverberation.":[18],"employ":[20],"the":[21,31,38,55,79,82,93,122],"notion":[22],"of":[23,57,81,115],"an":[24,62,106],"ideal":[25,107,129],"time-frequency":[26,43],"binary":[27,108,130],"mask,":[28],"which":[29,52],"selects":[30],"target":[32,67,74],"if":[33],"it":[34],"is":[35,102],"stronger":[36],"than":[37],"in":[40,98,113],"local":[42],"(T-F)":[44],"unit.":[45],"As":[46],"opposed":[47],"to":[48,87,104,128],"classical":[49],"adaptive":[50,63],"filtering,":[51],"focuses":[53],"on":[54],"suppression":[56],"noise,":[58],"our":[59],"model":[60],"employs":[61],"filter":[64],"that":[65,121],"performs":[66],"cancellation.":[68],"T-F":[69,100],"units":[70,88],"dominated":[71,89],"are":[75],"largely":[76],"suppressed":[77],"at":[78],"output":[80],"cancellation":[83],"unit":[84,101],"when":[85],"compared":[86],"noise.":[91],"Consequently,":[92],"actual":[94],"input-to-output":[95],"attenuation":[96],"level":[97],"each":[99],"used":[103],"estimate":[105],"mask.":[109],"A":[110],"systematic":[111],"evaluation":[112],"terms":[114],"automatic":[116],"speech":[117],"recognition":[118],"performance":[119],"shows":[120],"resulting":[123],"system":[124],"produces":[125],"masks":[126],"close":[127],"ones.":[131]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}