{"id":"https://openalex.org/W2034763797","doi":"https://doi.org/10.1109/icassp.2002.5743966","title":"Location-based sound segregation","display_name":"Location-based sound segregation","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2034763797","doi":"https://doi.org/10.1109/icassp.2002.5743966","mag":"2034763797"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743966","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743966","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"IEEE International Conference on Acoustics Speech and Signal Processing","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/A5053306339","display_name":"Nicoleta Roman","orcid":"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":true,"raw_author_name":"Nicoleta Roman","raw_affiliation_strings":["Department of Computer and Information Science and Center for Cognitive Science, Ohio State Uinversity, Columbus, OH, USA","Department of Computer and Information Science and Center for Cognitive Science, The Ohio State University, Columbus, 43210, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science and Center for Cognitive Science, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer and Information Science and Center for Cognitive Science, The Ohio State University, Columbus, 43210, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","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 and Information Science and Center for Cognitive Science, Ohio State Uinversity, Columbus, OH, USA","Department of Computer and Information Science and Center for Cognitive Science, The Ohio State University, Columbus, 43210, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science and Center for Cognitive Science, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer and Information Science and Center for Cognitive Science, The Ohio State University, Columbus, 43210, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080527909","display_name":"Guy J. Brown","orcid":"https://orcid.org/0000-0001-8565-5476"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Guy J. Brown","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, Sheffield, UK","Department of Computer Science, University of Sheffield, 211 Portobello Street, S1 4DP, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, 211 Portobello Street, S1 4DP, UK","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053306339"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.3298,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.44225834,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"I","last_page":"1013"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.8778135180473328},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7102863788604736},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.6496975421905518},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.5951189994812012},{"id":"https://openalex.org/keywords/critical-band","display_name":"Critical band","score":0.562762975692749},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.5581221580505371},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5453462600708008},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5289475917816162},{"id":"https://openalex.org/keywords/ideal","display_name":"Ideal (ethics)","score":0.479825496673584},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4792773425579071},{"id":"https://openalex.org/keywords/auditory-scene-analysis","display_name":"Auditory scene analysis","score":0.4767642617225647},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4752090871334076},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4718097448348999},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.45030295848846436},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4146055579185486},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34067302942276},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.24332976341247559},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.15204885601997375},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13371416926383972},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10757783055305481}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.8778135180473328},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7102863788604736},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.6496975421905518},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.5951189994812012},{"id":"https://openalex.org/C96390635","wikidata":"https://www.wikidata.org/wiki/Q366708","display_name":"Critical band","level":2,"score":0.562762975692749},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.5581221580505371},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5453462600708008},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5289475917816162},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.479825496673584},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4792773425579071},{"id":"https://openalex.org/C38129911","wikidata":"https://www.wikidata.org/wiki/Q4820038","display_name":"Auditory scene analysis","level":3,"score":0.4767642617225647},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4752090871334076},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4718097448348999},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.45030295848846436},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4146055579185486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34067302942276},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.24332976341247559},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.15204885601997375},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13371416926383972},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10757783055305481},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2002.5743966","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743966","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.112.6745","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.112.6745","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/RWB.ijcnn02.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.123.1661","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.123.1661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dcs.shef.ac.uk/~guy/pdf/ijcnn2002.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.131.9906","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.131.9906","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/RWB.icassp02.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4399999976158142,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W287108988","https://openalex.org/W1519903322","https://openalex.org/W1581848821","https://openalex.org/W1946152311","https://openalex.org/W1956364622","https://openalex.org/W1971031477","https://openalex.org/W1979493366","https://openalex.org/W2044222806","https://openalex.org/W2074354966","https://openalex.org/W2097191389","https://openalex.org/W2106325442","https://openalex.org/W3124666641","https://openalex.org/W3141144398","https://openalex.org/W4233014035","https://openalex.org/W4256399001","https://openalex.org/W6676076978","https://openalex.org/W6789284391","https://openalex.org/W6792116390"],"related_works":["https://openalex.org/W2005858633","https://openalex.org/W1985162360","https://openalex.org/W2081710558","https://openalex.org/W2082143966","https://openalex.org/W2090429267","https://openalex.org/W2055645765","https://openalex.org/W1995913400","https://openalex.org/W2156229416","https://openalex.org/W1982623997","https://openalex.org/W2052455788"],"abstract_inverted_index":{"At":[0],"a":[1,9,27,33,65,73,99],"cocktail":[2],"party,":[3],"we":[4,114],"can":[5],"selectively":[6],"attend":[7],"to":[8,21,78,88,120,137],"single":[10],"voice":[11],"and":[12,141],"filter":[13],"out":[14],"all":[15],"the":[16,45,55,62,79,83,89,109,130],"other":[17],"acoustical":[18],"interferences.":[19],"How":[20],"simulate":[22],"this":[23,103],"perceptual":[24],"ability":[25],"remains":[26],"great":[28],"challenge.":[29],"This":[30],"paper":[31],"describes":[32],"novel":[34],"location-based":[35],"approach":[36],"for":[37,95],"speech":[38],"segregation.":[39],"The":[40],"auditory":[41],"masking":[42],"effect":[43],"motivates":[44],"notion":[46],"of":[47,82],"an":[48],"\u201cideal\u201d":[49],"time-frequency":[50,67],"binary":[51,123,139],"mask,":[52],"which":[53],"selects":[54],"target":[56,84],"if":[57],"it":[58],"is":[59],"stronger":[60],"than":[61],"interference":[63],"in":[64,108,118],"local":[66],"region.":[68],"We":[69],"observe":[70],"that":[71,129],"within":[72],"narrow":[74],"frequency":[75],"band":[76],"modifications":[77],"relative":[80],"energy":[81,91],"source":[85],"with":[86],"respect":[87],"interfering":[90],"trigger":[92],"systematic":[93,126],"deviations":[94],"binaural":[96,110],"cues.":[97],"For":[98],"given":[100],"spatial":[101],"configuration,":[102],"interaction":[104],"produces":[105,133],"characteristic":[106],"clustering":[107],"feature":[111],"space.":[112],"Consequently,":[113],"perform":[115],"pattern":[116],"classification":[117],"order":[119],"estimate":[121],"ideal":[122,138],"masks.":[124],"A":[125],"evaluation":[127],"shows":[128],"resulting":[131],"system":[132],"masks":[134],"very":[135],"close":[136],"ones,":[140],"large":[142],"improvement":[143],"over":[144],"previous":[145],"models.":[146]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}