{"id":"https://openalex.org/W4294891356","doi":"https://doi.org/10.1109/taslp.2022.3202129","title":"Multi-Channel Talker-Independent Speaker Separation Through Location-Based Training","display_name":"Multi-Channel Talker-Independent Speaker Separation Through Location-Based Training","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4294891356","doi":"https://doi.org/10.1109/taslp.2022.3202129"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3202129","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3202129","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/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":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0002-7548-3081","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, 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":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0001-5073-8060","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, 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"},"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 Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0001-8195-6319","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, 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":3.9592,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.94733134,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"30","issue":null,"first_page":"2791","last_page":"2800"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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":0.6907398104667664},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6398564577102661},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.6291079521179199},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.56766277551651},{"id":"https://openalex.org/keywords/azimuth","display_name":"Azimuth","score":0.5668832063674927},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5413700342178345},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.42475634813308716},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.42058566212654114},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36483392119407654},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35321903228759766},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3423428237438202},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2079380452632904},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1417040228843689}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6907398104667664},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6398564577102661},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.6291079521179199},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.56766277551651},{"id":"https://openalex.org/C159737794","wikidata":"https://www.wikidata.org/wiki/Q124274","display_name":"Azimuth","level":2,"score":0.5668832063674927},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5413700342178345},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.42475634813308716},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.42058566212654114},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36483392119407654},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35321903228759766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3423428237438202},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2079380452632904},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1417040228843689},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3202129","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3202129","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2516952554","display_name":null,"funder_award_id":"ECCS-2125074","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G8472649251","display_name":null,"funder_award_id":"ECCS-1808932","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"}],"funders":[{"id":"https://openalex.org/F4320317189","display_name":"Ohio Supercomputer Center","ror":"https://ror.org/01apna436"},{"id":"https://openalex.org/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1964538581","https://openalex.org/W2031647436","https://openalex.org/W2044541911","https://openalex.org/W2046317813","https://openalex.org/W2073729956","https://openalex.org/W2087368178","https://openalex.org/W2117678320","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2291877678","https://openalex.org/W2304609584","https://openalex.org/W2516001803","https://openalex.org/W2734774145","https://openalex.org/W2750446090","https://openalex.org/W2763188033","https://openalex.org/W2803322398","https://openalex.org/W2804228164","https://openalex.org/W2889992917","https://openalex.org/W2892163332","https://openalex.org/W2897977894","https://openalex.org/W2900893004","https://openalex.org/W2939360348","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2972460025","https://openalex.org/W2972541922","https://openalex.org/W2972949456","https://openalex.org/W2982102024","https://openalex.org/W2982456909","https://openalex.org/W3008283340","https://openalex.org/W3015372568","https://openalex.org/W3015788098","https://openalex.org/W3016094953","https://openalex.org/W3016257794","https://openalex.org/W3094380169","https://openalex.org/W3099330747","https://openalex.org/W3132830522","https://openalex.org/W3162863443","https://openalex.org/W3171278394","https://openalex.org/W3197823486","https://openalex.org/W3206110053","https://openalex.org/W3217000580","https://openalex.org/W4205664022","https://openalex.org/W4210402803","https://openalex.org/W4214498238","https://openalex.org/W4233385860","https://openalex.org/W4233392025","https://openalex.org/W6769802879"],"related_works":["https://openalex.org/W2267473885","https://openalex.org/W1879255185","https://openalex.org/W2769861442","https://openalex.org/W4223965079","https://openalex.org/W1980506188","https://openalex.org/W4240587264","https://openalex.org/W2900122540","https://openalex.org/W2963983801","https://openalex.org/W3119734852","https://openalex.org/W2804363668"],"abstract_inverted_index":{"Permutation":[0],"ambiguity":[1,28,47],"is":[2,109],"a":[3,69,98,117,122,149,179],"crucial":[4],"issue":[5],"for":[6],"deep":[7],"learning":[8],"based":[9],"talker-independent":[10],"speaker":[11,78,143],"separation.":[12,79],"Deep":[13],"clustering":[14],"and":[15,139,145,163,170,186],"permutation":[16,27,46],"invariant":[17],"training":[18,67,100,136,181],"(PIT)":[19],"have":[20,36],"been":[21,37],"widely":[22],"used":[23],"to":[24,39,72,91,102,129,148,183],"address":[25],"the":[26,45,55,103],"problem":[29,48],"in":[30,76,94,171],"monaural":[31],"scenarios.":[32],"Although":[33],"both":[34],"approaches":[35],"extended":[38],"multi-microphone":[40],"scenarios,":[41],"we":[42,64,133,177],"believe":[43],"that":[44,82,156],"can":[49],"be":[50,130],"naturally":[51],"avoided":[52],"by":[53],"leveraging":[54],"spatial":[56],"relations":[57],"of":[58,105,125],"multiple":[59],"speakers.":[60],"In":[61,175],"this":[62],"study,":[63],"present":[65],"location-based":[66],"(LBT),":[68],"new":[70],"approach":[71],"achieve":[73],"talker":[74],"independency":[75],"multi-channel":[77],"Unlike":[80],"PIT":[81,115,160],"examines":[83],"all":[84],"possible":[85],"permutations,":[86],"LBT":[87,108,157],"assigns":[88],"speakers":[89,127],"according":[90],"their":[92],"positions":[93],"physical":[95],"space.":[96],"With":[97],"linear":[99],"complexity":[101],"number":[104,124],"concurrent":[106],"speakers,":[107],"computationally":[110],"much":[111],"more":[112],"efficient":[113],"than":[114],"with":[116,166],"factorial":[118],"complexity,":[119],"particularly":[120],"when":[121],"large":[123],"overlapping":[126],"needs":[128],"separated.":[131],"Specifically,":[132],"propose":[134,178],"two":[135],"criteria:":[137],"azimuth-based":[138,185],"distance-based":[140,187],"training,":[141,188],"using":[142],"azimuths":[144],"distances":[146],"relative":[147],"microphone":[150],"array,":[151],"respectively.":[152],"Evaluation":[153],"results":[154],"show":[155],"significantly":[158],"outperforms":[159],"on":[161],"two-speaker":[162],"three-speaker":[164],"mixtures":[165],"different":[167],"array":[168],"geometries":[169],"various":[172],"acoustic":[173],"conditions.":[174],"addition,":[176],"joint":[180],"strategy":[182],"integrate":[184],"which":[189],"further":[190],"improves":[191],"separation":[192],"performance.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}