{"id":"https://openalex.org/W4319586547","doi":"https://doi.org/10.1109/iscslp57327.2022.10037846","title":"TSUP Speaker Diarization System for Conversational Short-phrase Speaker Diarization Challenge","display_name":"TSUP Speaker Diarization System for Conversational Short-phrase Speaker Diarization Challenge","publication_year":2022,"publication_date":"2022-12-11","ids":{"openalex":"https://openalex.org/W4319586547","doi":"https://doi.org/10.1109/iscslp57327.2022.10037846"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp57327.2022.10037846","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10037846","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5009469573","display_name":"Bowen Pang","orcid":"https://orcid.org/0000-0003-4312-5869"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bowen Pang","raw_affiliation_strings":["Northwestern Polytechnical University (NPU),Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University (NPU),Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011902043","display_name":"Huan Zhao","orcid":"https://orcid.org/0000-0002-3133-3137"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huan Zhao","raw_affiliation_strings":["Northwestern Polytechnical University (NPU),Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University (NPU),Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038536579","display_name":"Gaosheng Zhang","orcid":"https://orcid.org/0000-0003-4940-712X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gaosheng Zhang","raw_affiliation_strings":["Shenzhen Transsion Holding Limited"],"affiliations":[{"raw_affiliation_string":"Shenzhen Transsion Holding Limited","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017050448","display_name":"Xiaoyue Yang","orcid":"https://orcid.org/0000-0002-0483-6249"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoyue Yang","raw_affiliation_strings":["Shenzhen Transsion Holding Limited"],"affiliations":[{"raw_affiliation_string":"Shenzhen Transsion Holding Limited","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101448099","display_name":"Yang Sun","orcid":"https://orcid.org/0000-0002-3164-5747"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Sun","raw_affiliation_strings":["Shenzhen Transsion Holding Limited"],"affiliations":[{"raw_affiliation_string":"Shenzhen Transsion Holding Limited","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100425399","display_name":"Li Zhang","orcid":"https://orcid.org/0000-0001-5077-9962"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhang","raw_affiliation_strings":["Northwestern Polytechnical University (NPU),Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University (NPU),Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107808955","display_name":"Qing Wang","orcid":"https://orcid.org/0009-0008-5449-4815"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Wang","raw_affiliation_strings":["Northwestern Polytechnical University (NPU),Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University (NPU),Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University (NPU),Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University (NPU),Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5009469573"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.7276,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.72430511,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"502","last_page":"506"},"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/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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9973000288009644,"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":0.9713160991668701},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.6567582488059998},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6525160670280457},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6450225114822388},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5133542418479919},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.42488011717796326},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32299357652664185},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06294557452201843}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9713160991668701},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.6567582488059998},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6525160670280457},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6450225114822388},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5133542418479919},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.42488011717796326},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32299357652664185},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06294557452201843},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp57327.2022.10037846","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10037846","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W2081074144","https://openalex.org/W2132914434","https://openalex.org/W2158703410","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2611199340","https://openalex.org/W2726515241","https://openalex.org/W2890964092","https://openalex.org/W2936774411","https://openalex.org/W2963470929","https://openalex.org/W2963745998","https://openalex.org/W2969985801","https://openalex.org/W2972949456","https://openalex.org/W2997419692","https://openalex.org/W3008357631","https://openalex.org/W3015598461","https://openalex.org/W3024869864","https://openalex.org/W3025260599","https://openalex.org/W3033627755","https://openalex.org/W3105031100","https://openalex.org/W3128434617","https://openalex.org/W3140898556","https://openalex.org/W3147778289","https://openalex.org/W3162347631","https://openalex.org/W3196595845","https://openalex.org/W3197980326","https://openalex.org/W3198455895","https://openalex.org/W3198858272","https://openalex.org/W3206479921","https://openalex.org/W3207834622","https://openalex.org/W3212886388","https://openalex.org/W4214556932","https://openalex.org/W4221167533","https://openalex.org/W4224916733","https://openalex.org/W4297841547","https://openalex.org/W4319586574","https://openalex.org/W4385245566","https://openalex.org/W6631362777","https://openalex.org/W6688816777","https://openalex.org/W6744964450","https://openalex.org/W6779069803","https://openalex.org/W6800885585","https://openalex.org/W6801496586","https://openalex.org/W6809668307"],"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":{"This":[0],"paper":[1],"describes":[2],"the":[3,8,72,79,84,109,122,126,135,139],"TSUP":[4],"team\u2019s":[5],"submission":[6],"to":[7,94],"ISCSLP":[9],"2022":[10],"conversational":[11,29],"short-phrase":[12,21],"speaker":[13,43,101],"diarization":[14,30,44,61,102],"(CSSD)":[15],"challenge":[16,127],"which":[17,46],"particularly":[18],"focuses":[19],"on":[20,90,125],"conversations":[22],"with":[23],"a":[24],"new":[25,85],"evaluation":[26],"metric":[27,124],"called":[28],"error":[31],"rate":[32],"(CDER).":[33],"In":[34],"this":[35],"challenge,":[36],"we":[37],"explore":[38],"three":[39,98],"kinds":[40],"of":[41,100,111],"typical":[42],"systems,":[45],"are":[47,67],"spectral":[48],"clustering":[49],"(SC)":[50],"based":[51],"diarization,":[52],"target-speaker":[53],"voice":[54],"activity":[55],"detection":[56],"(TS-VAD)":[57],"and":[58],"end-to-end":[59],"neural":[60],"(EEND)":[62],"respectively.":[63],"Our":[64,129],"major":[65],"findings":[66],"summarized":[68],"as":[69],"follows.":[70],"First,":[71],"SC":[73,131],"approach":[74],"is":[75,92],"more":[76],"favored":[77],"over":[78],"other":[80],"two":[81],"approaches":[82],"under":[83],"CDER":[86,95,105,123],"metric.":[87],"Second,":[88],"tuning":[89],"hyperparameters":[91],"essential":[93],"for":[96],"all":[97],"types":[99],"systems.":[103],"Specifically,":[104],"becomes":[106],"smaller":[107],"when":[108],"length":[110],"sub-segments":[112],"setting":[113],"longer.":[114],"Finally,":[115],"multi-system":[116],"fusion":[117],"through":[118],"DOVER-LAP":[119],"will":[120],"worsen":[121],"data.":[128],"submitted":[130],"system":[132],"eventually":[133],"ranks":[134],"third":[136],"place":[137],"in":[138],"challenge.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}