{"id":"https://openalex.org/W4224933752","doi":"https://doi.org/10.1109/icassp43922.2022.9746354","title":"Improving Separation-Based Speaker Diarization Via Iterative Model Refinement And Speaker Embedding Based Post-Processing","display_name":"Improving Separation-Based Speaker Diarization Via Iterative Model Refinement And Speaker Embedding Based Post-Processing","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224933752","doi":"https://doi.org/10.1109/icassp43922.2022.9746354"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746354","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746354","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":"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/A5064699619","display_name":"Shutong Niu","orcid":"https://orcid.org/0000-0003-0315-1042"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shu-Tong Niu","raw_affiliation_strings":["University of Science and Technology of China,Hefei,P. R. China","University of Science and Technology of China, Hefei, P. R. China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["University of Science and Technology of China,Hefei,P. R. China","University of Science and Technology of China, Hefei, P. R. China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101926390","display_name":"Lei Sun","orcid":"https://orcid.org/0000-0001-7680-6455"},"institutions":[{"id":"https://openalex.org/I39774598","display_name":"Hefei University","ror":"https://ror.org/01f5rdf64","country_code":"CN","type":"education","lineage":["https://openalex.org/I39774598"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Sun","raw_affiliation_strings":["iFlytek Research,Hefei,P. R. China","iFlytek Research, Hefei, P. R. China"],"affiliations":[{"raw_affiliation_string":"iFlytek Research,Hefei,P. R. China","institution_ids":["https://openalex.org/I39774598"]},{"raw_affiliation_string":"iFlytek Research, Hefei, P. R. China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA,USA","Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5064699619"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.3687,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.47424961,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":"28","issue":null,"first_page":"8387","last_page":"8391"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9983000159263611,"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":0.8813794851303101},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8067305684089661},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6437466740608215},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5393990874290466},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.342029869556427}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8813794851303101},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8067305684089661},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6437466740608215},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5393990874290466},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.342029869556427}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746354","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746354","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":[{"display_name":"Quality Education","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2038101708","https://openalex.org/W2046056978","https://openalex.org/W2098726438","https://openalex.org/W2144125830","https://openalex.org/W2150769028","https://openalex.org/W2194775991","https://openalex.org/W2345067732","https://openalex.org/W2460742184","https://openalex.org/W2726515241","https://openalex.org/W2800664709","https://openalex.org/W2890964092","https://openalex.org/W2939690918","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2972949456","https://openalex.org/W2989790778","https://openalex.org/W3015522062","https://openalex.org/W3024085360","https://openalex.org/W3025260599","https://openalex.org/W3096893582","https://openalex.org/W3099330747","https://openalex.org/W3140898556","https://openalex.org/W3162347631","https://openalex.org/W3182885906","https://openalex.org/W3197980326","https://openalex.org/W3212886388","https://openalex.org/W4297788887","https://openalex.org/W6629717138","https://openalex.org/W6662018943","https://openalex.org/W6682600690","https://openalex.org/W6766542914","https://openalex.org/W6770053191","https://openalex.org/W6779429391","https://openalex.org/W6790122275","https://openalex.org/W6798708994"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W1521049138","https://openalex.org/W2144208207","https://openalex.org/W1813780412","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2148232863","https://openalex.org/W2160753975","https://openalex.org/W2161543916"],"abstract_inverted_index":{"In":[0,19],"this":[1],"paper,":[2],"we":[3,23,61],"propose":[4,67],"an":[5],"iterative":[6],"separation-based":[7],"speaker":[8,30,49,63,72,75,99],"diarization":[9,80,100,121],"(ISSD)":[10],"approach":[11,106],"to":[12,29,39,53,96,139],"cope":[13],"with":[14,108],"the":[15,20,34,79,83,103,109,126,140],"realistic":[16],"data":[17,27,89],"conditions.":[18],"proposed":[21,104],"ISSD,":[22,60],"iteratively":[24],"generate":[25],"adaptation":[26],"ac-cording":[28],"priors":[31],"and":[32,66,74,117,128],"fine-tune":[33],"separation":[35],"model,":[36],"which":[37],"leads":[38],"a":[40,114],"gradual":[41],"performance":[42,81],"improvement.":[43],"To":[44],"further":[45],"reduce":[46],"some":[47,54],"unavoidable":[48],"detection":[50],"errors":[51,57],"due":[52],"undesirable":[55],"prior":[56],"using":[58],"simple":[59],"utilize":[62],"embedding":[64],"information":[65],"two":[68,110],"post-processing":[69,111],"techniques,":[70],"namely,":[71],"filtering":[73],"recovery.":[76],"We":[77],"evaluate":[78],"on":[82,125],"two-speaker":[84],"conversational":[85],"telephone":[86],"speech":[87],"(CTS)":[88],"set":[90],"from":[91],"DIHARD-III":[92,144],"Challenge.":[93,145],"When":[94],"compared":[95],"state-of-the-art":[97],"clustering-based":[98],"(CSD)":[101],"system,":[102],"ISSD":[105,132],"combined":[107],"schemes":[112],"yields":[113],"47.72":[115],"%":[116,119],"46.97":[118],"relative":[120],"error":[122],"rate":[123],"reduction":[124],"development":[127],"evaluation":[129],"sets,":[130],"respectively.":[131],"is":[133],"also":[134],"one":[135],"key":[136],"contributing":[137],"factor":[138],"best-performing":[141],"system":[142],"in":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}