{"id":"https://openalex.org/W4395471098","doi":"https://doi.org/10.1109/taslp.2024.3393726","title":"Multi-Channel Conversational Speaker Separation via Neural Diarization","display_name":"Multi-Channel Conversational Speaker Separation via Neural Diarization","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4395471098","doi":"https://doi.org/10.1109/taslp.2024.3393726"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3393726","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3393726","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":true,"raw_author_name":"Hassan Taherian","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"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"],"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":2,"corresponding_author_ids":["https://openalex.org/A5073861062"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":7.0085,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.97837898,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"32","issue":null,"first_page":"2467","last_page":"2476"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.8595162034034729},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5758074522018433},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5350286960601807},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4620479941368103},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4394893944263458},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.34160375595092773},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10300624370574951},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.037600189447402954}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8595162034034729},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5758074522018433},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5350286960601807},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4620479941368103},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4394893944263458},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.34160375595092773},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10300624370574951},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.037600189447402954}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3393726","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3393726","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":[],"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"}],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W262275730","https://openalex.org/W1494198834","https://openalex.org/W2159591770","https://openalex.org/W2164502538","https://openalex.org/W2221409856","https://openalex.org/W2291877678","https://openalex.org/W2734774145","https://openalex.org/W2890964092","https://openalex.org/W2900212944","https://openalex.org/W2962780374","https://openalex.org/W2962866211","https://openalex.org/W2972818416","https://openalex.org/W2972949456","https://openalex.org/W3007256793","https://openalex.org/W3007328579","https://openalex.org/W3016031604","https://openalex.org/W3016232124","https://openalex.org/W3020336359","https://openalex.org/W3025260599","https://openalex.org/W3094380169","https://openalex.org/W3094831814","https://openalex.org/W3160936850","https://openalex.org/W3161590371","https://openalex.org/W3162863443","https://openalex.org/W3163842642","https://openalex.org/W3171278394","https://openalex.org/W3182358018","https://openalex.org/W3185109982","https://openalex.org/W3197823486","https://openalex.org/W3204618061","https://openalex.org/W3207728800","https://openalex.org/W3209238651","https://openalex.org/W3209984917","https://openalex.org/W3212886388","https://openalex.org/W4210402803","https://openalex.org/W4220731890","https://openalex.org/W4226016254","https://openalex.org/W4294891356","https://openalex.org/W4313417891","https://openalex.org/W4372270835","https://openalex.org/W4375869047","https://openalex.org/W4385245566","https://openalex.org/W4385756463","https://openalex.org/W4385822256","https://openalex.org/W4390660238","https://openalex.org/W4391621214","https://openalex.org/W4392908986"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"When":[0],"dealing":[1],"with":[2,170],"overlapped":[3],"speech,":[4],"the":[5,50,88,110,115,124,133,142,156,189],"performance":[6,25],"of":[7,55,91,104,112,117,128],"automatic":[8],"speech":[9,57,89],"recognition":[10],"(ASR)":[11],"systems":[12],"substantially":[13],"degrades":[14],"as":[15],"they":[16],"are":[17],"designed":[18],"for":[19,76,177],"single-talker":[20],"speech.":[21],"To":[22,59],"enhance":[23],"ASR":[24,197],"in":[26,107],"conversational":[27],"or":[28],"meeting":[29,77],"environments,":[30],"continuous":[31],"speaker":[32,98,130],"separation":[33,43,71,120,131,143,186],"(CSS)":[34],"is":[35,174],"commonly":[36],"employed.":[37],"However,":[38],"CSS":[39],"requires":[40],"a":[41,65,102,118,200],"short":[42],"window":[44,51],"to":[45,86,114,152,155,163],"avoid":[46],"many":[47],"speakers":[48,113,151],"inside":[49],"and":[52,185,196],"sequential":[53],"grouping":[54],"discontinuous":[56],"segments.":[58],"address":[60],"these":[61],"limitations,":[62],"we":[63,100],"introduce":[64],"new":[66],"multi-channel":[67],"framework":[68],"called":[69],"\u201cspeaker":[70],"via":[72],"neural":[73],"diarization\u201d":[74],"(SSND)":[75],"environments.":[78],"Our":[79],"approach":[80,147],"utilizes":[81],"an":[82],"end-to-end":[83],"diarization":[84,134,184,195],"system":[85],"identify":[87],"activity":[90],"each":[92],"individual":[93],"speaker.":[94],"By":[95],"leveraging":[96],"estimated":[97],"boundaries,":[99],"generate":[101],"sequence":[103],"embeddings,":[105],"which":[106],"turn":[108],"facilitate":[109],"assignment":[111],"outputs":[116],"multi-talker":[119],"model.":[121],"SSND":[122,173],"addresses":[123],"permutation":[125],"ambiguity":[126],"issue":[127],"talker-independent":[129],"during":[132,141],"phase":[135],"through":[136],"location-based":[137],"training,":[138],"rather":[139],"than":[140],"process.":[144],"This":[145],"unique":[146],"allows":[148],"multiple":[149],"non-overlapped":[150],"be":[153],"assigned":[154],"same":[157],"output":[158],"stream,":[159],"making":[160],"it":[161],"possible":[162],"efficiently":[164],"process":[165],"long":[166],"segments-a":[167],"task":[168],"impossible":[169],"CSS.":[171],"Additionally,":[172],"naturally":[175],"suitable":[176],"speaker-attributed":[178],"ASR.":[179],"We":[180],"evaluate":[181],"our":[182],"proposed":[183],"methods":[187],"on":[188],"open":[190],"LibriCSS":[191],"dataset,":[192],"advancing":[193],"state-of-the-art":[194],"results":[198],"by":[199],"large":[201],"margin.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}