{"id":"https://openalex.org/W3206110053","doi":"https://doi.org/10.1109/icassp43922.2022.9747141","title":"Location-Based Training for Multi-Channel Talker-Independent Speaker Separation","display_name":"Location-Based Training for Multi-Channel Talker-Independent Speaker Separation","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3206110053","doi":"https://doi.org/10.1109/icassp43922.2022.9747141","mag":"3206110053"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747141","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747141","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 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/A5073861062","display_name":"Hassan Taherian","orcid":"https://orcid.org/0000-0002-7548-3081"},"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":"Hassan Taherian","raw_affiliation_strings":["The Ohio State University,Department of Computer Science and Engineering,USA","Department of Computer Science and Engineering, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University,Department of Computer Science and Engineering,USA","institution_ids":["https://openalex.org/I52357470"]},{"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/A5058209019","display_name":"Ke Tan","orcid":"https://orcid.org/0000-0001-5073-8060"},"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":"Ke Tan","raw_affiliation_strings":["The Ohio State University,Department of Computer Science and Engineering,USA","Department of Computer Science and Engineering, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University,Department of Computer Science and Engineering,USA","institution_ids":["https://openalex.org/I52357470"]},{"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":["The Ohio State University,Department of Computer Science and Engineering,USA","Center for Cognitive and Brain Sciences, The Ohio State University, USA","Department of Computer Science and Engineering, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University,Department of Computer Science and Engineering,USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]},{"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":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":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"696","last_page":"700"},"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":0.9987999796867371,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/azimuth","display_name":"Azimuth","score":0.8182439804077148},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7070241570472717},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6143246293067932},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5430294275283813},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5405769348144531},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.5099598169326782},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4925287663936615},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.45321956276893616},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.43371185660362244},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.420957088470459},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.4187273383140564},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3692569136619568},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.357311487197876},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3430122137069702},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.18748456239700317},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18673497438430786},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.11271047592163086},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0760454535484314}],"concepts":[{"id":"https://openalex.org/C159737794","wikidata":"https://www.wikidata.org/wiki/Q124274","display_name":"Azimuth","level":2,"score":0.8182439804077148},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7070241570472717},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6143246293067932},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5430294275283813},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5405769348144531},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.5099598169326782},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4925287663936615},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.45321956276893616},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.43371185660362244},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.420957088470459},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.4187273383140564},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3692569136619568},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.357311487197876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3430122137069702},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.18748456239700317},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18673497438430786},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11271047592163086},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0760454535484314},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747141","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747141","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320317189","display_name":"Ohio Supercomputer Center","ror":"https://ror.org/01apna436"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1581848821","https://openalex.org/W2046317813","https://openalex.org/W2117678320","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2291877678","https://openalex.org/W2734774145","https://openalex.org/W2763188033","https://openalex.org/W2897977894","https://openalex.org/W2962866211","https://openalex.org/W2972460025","https://openalex.org/W2972949456","https://openalex.org/W2982102024","https://openalex.org/W3008283340","https://openalex.org/W3015199127","https://openalex.org/W3015679215","https://openalex.org/W3035268204","https://openalex.org/W3094380169","https://openalex.org/W3132830522","https://openalex.org/W3162863443","https://openalex.org/W3171278394","https://openalex.org/W3185109982","https://openalex.org/W3197823486","https://openalex.org/W6774995033","https://openalex.org/W6791509883"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2769861442","https://openalex.org/W4223965079","https://openalex.org/W2120442551","https://openalex.org/W1980506188","https://openalex.org/W2112728813","https://openalex.org/W4240587264","https://openalex.org/W2011788874","https://openalex.org/W2900122540","https://openalex.org/W2963983801"],"abstract_inverted_index":{"Permutation-invariant":[0],"training":[1,28,43,55,94,100,118,135],"(PIT)":[2],"is":[3,57],"a":[4,26,133],"dominant":[5],"approach":[6,29],"for":[7,34,80,159],"addressing":[8],"the":[9,48,103,121,140,147,155,160],"permutation":[10,32],"ambiguity":[11],"problem":[12],"in":[13,68],"talker-independent":[14],"speaker":[15,36,107],"separation.":[16,37],"Leveraging":[17],"spatial":[18,52],"information":[19],"afforded":[20],"by":[21,119],"microphone":[22],"arrays,":[23],"we":[24,112],"propose":[25],"new":[27],"to":[30,59,65,139,146],"resolving":[31],"ambiguities":[33],"multi-channel":[35],"The":[38],"proposed":[39],"approach,":[40],"named":[41],"location-based":[42,81],"(LBT),":[44],"assigns":[45],"speakers":[46,63],"on":[47,85],"basis":[49],"of":[50,123,142,150,157,162],"their":[51,66],"locations.":[53],"This":[54],"strategy":[56],"easy":[58],"apply,":[60],"and":[61,77,88,98,164],"organizes":[62],"according":[64],"positions":[67],"physical":[69],"space.":[70],"Specifically,":[71],"this":[72],"study":[73],"investigates":[74],"azimuth":[75],"angles":[76],"source":[78],"distances":[79],"training.":[82],"Evaluation":[83],"results":[84],"separating":[86],"two-":[87],"three-speaker":[89],"mixtures":[90],"show":[91],"that":[92],"azimuth-based":[93,115],"consistently":[95],"outperforms":[96],"PIT,":[97],"distance-based":[99,117],"further":[101,127,153],"improves":[102,128],"separation":[104,129,161],"performance":[105],"when":[106],"azimuths":[108,122],"are":[109],"close.":[110],"Furthermore,":[111],"dynamically":[113],"select":[114],"or":[116],"estimating":[120],"separated":[124],"speakers,":[125,143],"which":[126],"performance.":[130],"LBT":[131,158],"has":[132],"linear":[134],"complexity":[136,149],"with":[137],"respect":[138],"number":[141],"as":[144],"opposed":[145],"factorial":[148],"PIT.":[151],"We":[152],"demonstrate":[154],"effectiveness":[156],"four":[163],"five":[165],"concurrent":[166],"speakers.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-26T07:53:14.480251","created_date":"2025-10-10T00:00:00"}