{"id":"https://openalex.org/W4375869401","doi":"https://doi.org/10.1109/icassp49357.2023.10096436","title":"TOLD: a Novel Two-Stage Overlap-Aware Framework for Speaker Diarization","display_name":"TOLD: a Novel Two-Stage Overlap-Aware Framework for Speaker Diarization","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869401","doi":"https://doi.org/10.1109/icassp49357.2023.10096436"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096436","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096436","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5100631346","display_name":"Jiaming Wang","orcid":"https://orcid.org/0000-0001-9931-0209"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaming Wang","raw_affiliation_strings":["Speech Lab of DAMO Academy,Alibaba Group,China","Alibaba Group, Speech Lab of DAMO Academy, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab of DAMO Academy,Alibaba Group,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, Speech Lab of DAMO Academy, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001133136","display_name":"Zhihao Du","orcid":"https://orcid.org/0000-0003-3509-9322"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Du","raw_affiliation_strings":["Speech Lab of DAMO Academy,Alibaba Group,China","Alibaba Group, Speech Lab of DAMO Academy, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab of DAMO Academy,Alibaba Group,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, Speech Lab of DAMO Academy, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101777591","display_name":"Shiliang Zhang","orcid":"https://orcid.org/0000-0002-9524-1602"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiliang Zhang","raw_affiliation_strings":["Speech Lab of DAMO Academy,Alibaba Group,China","Alibaba Group, Speech Lab of DAMO Academy, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab of DAMO Academy,Alibaba Group,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, Speech Lab of DAMO Academy, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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":0.9991999864578247,"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":0.9465980529785156},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.796381413936615},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7259830236434937},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.653548538684845},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5417304039001465},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4988548755645752},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4945389926433563},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4564327299594879},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3775135576725006}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9465980529785156},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.796381413936615},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7259830236434937},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.653548538684845},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5417304039001465},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4988548755645752},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4945389926433563},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4564327299594879},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3775135576725006},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/icassp49357.2023.10096436","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096436","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2046056978","https://openalex.org/W2081074144","https://openalex.org/W2123768812","https://openalex.org/W2148613904","https://openalex.org/W2168941687","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2514794854","https://openalex.org/W2537749207","https://openalex.org/W2696967604","https://openalex.org/W2734774145","https://openalex.org/W2767895109","https://openalex.org/W2890964092","https://openalex.org/W2963470929","https://openalex.org/W2963962398","https://openalex.org/W2969985801","https://openalex.org/W2972680151","https://openalex.org/W2972949456","https://openalex.org/W3008357631","https://openalex.org/W3025260599","https://openalex.org/W3095212884","https://openalex.org/W3095822285","https://openalex.org/W3145204487","https://openalex.org/W3163019736","https://openalex.org/W3196857193","https://openalex.org/W3197916665","https://openalex.org/W4214556932","https://openalex.org/W4224925084","https://openalex.org/W4225661121","https://openalex.org/W4385245566","https://openalex.org/W4385573729","https://openalex.org/W6688816777","https://openalex.org/W6739901393","https://openalex.org/W6746195497"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W1521049138"],"abstract_inverted_index":{"Recently,":[0],"end-to-end":[1],"neural":[2],"diarization":[3,17,51,104,128],"(EEND)":[4],"is":[5,18,156],"introduced":[6],"and":[7,31,57,68,132],"achieves":[8,120,146],"promising":[9],"results":[10,105,109],"in":[11,64,125],"speaker-overlapped":[12],"scenarios.":[13],"In":[14],"EEND,":[15,116],"speaker":[16,26,50,66,95],"formulated":[19],"as":[20,52],"a":[21,53,85,94,121,141,147,157],"multi-label":[22],"prediction":[23],"problem,":[24],"where":[25],"activities":[27],"are":[28,34],"estimated":[29],"independently":[30],"their":[32],"dependency":[33,69],"not":[35],"well":[36],"considered.":[37],"To":[38],"overcome":[39],"these":[40],"disadvantages,":[41],"we":[42,82],"employ":[43],"the":[44,59,76,103,114,117,152,165],"power":[45],"set":[46],"encoding":[47],"to":[48,100,164],"reformulate":[49],"single-label":[54],"classification":[55],"problem":[56],"propose":[58,84],"overlap-aware":[60,96],"EEND":[61],"(EEND-OLA)":[62],"model,":[63],"which":[65,155],"overlaps":[67],"can":[70],"be":[71],"modeled":[72],"explicitly.":[73],"Inspired":[74],"by":[75,92],"success":[77],"of":[78,106,127,149,167],"two-stage":[79],"hybrid":[80],"systems,":[81],"further":[83],"novel":[86],"Two-stage":[87],"OverLap-aware":[88],"Diarization":[89],"framework":[90],"(TOLD)":[91],"involving":[93],"post-processing":[97],"(SOAP)":[98],"model":[99],"iteratively":[101],"refine":[102],"EEND-OLA.":[107],"Experimental":[108],"show":[110],"that,":[111],"compared":[112],"with":[113],"original":[115],"proposed":[118],"EEND-OLA":[119],"14.39%":[122],"relative":[123,138],"improvement":[124],"terms":[126],"error":[129],"rates":[130],"(DER),":[131],"utilizing":[133],"SOAP":[134],"provides":[135],"another":[136],"19.33%":[137],"improvement.":[139],"As":[140],"result,":[142],"our":[143,168],"method":[144],"TOLD":[145],"DER":[148],"10.14%":[150],"on":[151,161],"CALLHOME":[153],"dataset,":[154],"new":[158],"state-of-the-art":[159],"result":[160],"this":[162],"benchmark":[163],"best":[166],"knowledge.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}