{"id":"https://openalex.org/W2921428693","doi":"https://doi.org/10.23919/apsipa.2018.8659701","title":"An Analysis of Speaker Diarization Fusion Methods For The First DIHARD Challenge","display_name":"An Analysis of Speaker Diarization Fusion Methods For The First DIHARD Challenge","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2921428693","doi":"https://doi.org/10.23919/apsipa.2018.8659701","mag":"2921428693"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659701","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5085519273","display_name":"Bing Yin","orcid":"https://orcid.org/0000-0002-5890-0031"},"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":"Bing Yin","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of 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"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of 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/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":"Lei Sun","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101428754","display_name":"Xueyang Zhang","orcid":"https://orcid.org/0000-0002-6428-0414"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xueyang Zhang","raw_affiliation_strings":["iFlytek Research, China"],"affiliations":[{"raw_affiliation_string":"iFlytek Research, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114417892","display_name":"Shan He","orcid":"https://orcid.org/0000-0001-6965-6276"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shan He","raw_affiliation_strings":["iFlytek Research, China"],"affiliations":[{"raw_affiliation_string":"iFlytek Research, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"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":"Zhenhua Ling","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101922053","display_name":"Guoping Hu","orcid":"https://orcid.org/0000-0002-1276-6201"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guoping Hu","raw_affiliation_strings":["iFlytek Research, China"],"affiliations":[{"raw_affiliation_string":"iFlytek Research, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038369085","display_name":"Wu Guo","orcid":"https://orcid.org/0000-0002-3779-7944"},"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":"Wu Guo","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5085519273"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.1629,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.6213099,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"1473","last_page":"1477"},"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":0.9995999932289124,"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":0.9986000061035156,"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":0.8728954195976257},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.768298864364624},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7068184614181519},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6990991830825806},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6906947493553162},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4927976429462433},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4903090298175812},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4562664031982422},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44717100262641907},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.44695931673049927},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4225744605064392},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4039994180202484},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06159892678260803}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8728954195976257},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.768298864364624},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7068184614181519},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6990991830825806},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6906947493553162},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4927976429462433},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4903090298175812},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4562664031982422},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44717100262641907},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.44695931673049927},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4225744605064392},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4039994180202484},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06159892678260803},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/apsipa.2018.8659701","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W118310762","https://openalex.org/W184672293","https://openalex.org/W1608667326","https://openalex.org/W2024490156","https://openalex.org/W2040023846","https://openalex.org/W2096733369","https://openalex.org/W2101025008","https://openalex.org/W2121812409","https://openalex.org/W2150769028","https://openalex.org/W2168175751","https://openalex.org/W2170695863","https://openalex.org/W2283724112","https://openalex.org/W2316138215","https://openalex.org/W2612434969","https://openalex.org/W2612688029","https://openalex.org/W2726515241","https://openalex.org/W2802905931","https://openalex.org/W3099206234","https://openalex.org/W3208240190","https://openalex.org/W4285719527","https://openalex.org/W4300666183","https://openalex.org/W6607611041","https://openalex.org/W6682042307","https://openalex.org/W6699662792"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W4225315139","https://openalex.org/W4385881881"],"abstract_inverted_index":{"In":[0],"this":[1,19],"paper,":[2],"we":[3],"introduce":[4],"the":[5,12,21,32,35,106,111,115],"attempts":[6],"of":[7,34,103],"our":[8,17,54,96],"fusion":[9,86],"methods":[10],"during":[11],"first":[13,22],"DIHARD":[14,116],"challenge.":[15,117],"To":[16],"knowledge,":[18],"is":[20,69,87,110],"launch":[23],"in":[24,38,64,114],"speaker":[25],"diarization":[26,99],"domain":[27],"which":[28,109],"aims":[29],"to":[30,71],"evaluate":[31],"performance":[33],"state-of-the-art":[36],"system":[37,65,97],"realistic":[39],"adverse":[40],"acoustic":[41],"environments.":[42],"Besides":[43],"speech":[44,48,51,75],"preprocessing":[45],"modules":[46],"including":[47],"denoising":[49],"and":[50,76,92],"activity":[52],"detection,":[53],"attention":[55],"has":[56],"been":[57],"focused":[58],"on":[59,105],"back-end":[60],"clustering":[61,68],"algorithms,":[62],"especially":[63],"fusion.":[66],"Consensus":[67],"adopt":[70],"combine":[72],"both":[73],"original":[74],"denoised":[77],"speech,":[78],"for":[79],"purifying":[80],"unreliable":[81],"clusters.":[82],"Moreover,":[83],"a":[84],"score-level":[85],"conducted":[88],"between":[89],"GMM-UBM-based":[90],"i-vector":[91],"CNN-based":[93],"i-vector.":[94],"Finally,":[95],"achieves":[98],"error":[100],"rates":[101],"(DERs)":[102],"36.05%":[104],"evaluation":[107],"sets,":[108],"second":[112],"place":[113]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
