{"id":"https://openalex.org/W2040429011","doi":"https://doi.org/10.1109/iscslp.2012.6423465","title":"Intra-conversation intra-speaker variability compensation for speaker clustering","display_name":"Intra-conversation intra-speaker variability compensation for speaker clustering","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2040429011","doi":"https://doi.org/10.1109/iscslp.2012.6423465","mag":"2040429011"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2012.6423465","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2012.6423465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 8th International Symposium on Chinese Spoken Language Processing","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/A5029039334","display_name":"Kui Wu","orcid":"https://orcid.org/0000-0002-6857-7231"},"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":"Kui Wu","raw_affiliation_strings":["IFly Speech Laboratory, University of Science and Technology of China, China","iFly Speech Lab, University of Science and Technology of China (USTC), China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IFly Speech Laboratory, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"iFly Speech Lab, University of Science and Technology of China (USTC), China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381758","display_name":"Yan Song","orcid":"https://orcid.org/0000-0002-5668-9068"},"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":"Yan Song","raw_affiliation_strings":["IFly Speech Laboratory, University of Science and Technology of China, China","iFly Speech Lab, University of Science and Technology of China (USTC), China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IFly Speech Laboratory, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"iFly Speech Lab, University of Science and Technology of China (USTC), China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","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":["IFly Speech Laboratory, University of Science and Technology of China, China","iFly Speech Lab, University of Science and Technology of China (USTC), China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IFly Speech Laboratory, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"iFly Speech Lab, University of Science and Technology of China (USTC), China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"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":"LiRong Dai","raw_affiliation_strings":["IFly Speech Laboratory, University of Science and Technology of China, China","iFly Speech Lab, University of Science and Technology of China (USTC), China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IFly Speech Laboratory, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"iFly Speech Lab, University of Science and Technology of China (USTC), China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"330","last_page":"334"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9984999895095825,"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":0.9947999715805054,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8187496662139893},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.7839788198471069},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7187976241111755},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7025175094604492},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6960248947143555},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6703977584838867},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6489290595054626},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4232175350189209},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39866477251052856},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3689288794994354},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09020262956619263}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8187496662139893},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.7839788198471069},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7187976241111755},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7025175094604492},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6960248947143555},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6703977584838867},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6489290595054626},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4232175350189209},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39866477251052856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3689288794994354},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09020262956619263},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2012.6423465","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2012.6423465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 8th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W125260059","https://openalex.org/W204053250","https://openalex.org/W1532958172","https://openalex.org/W2115599677","https://openalex.org/W2125642021","https://openalex.org/W2150769028","https://openalex.org/W2151101344","https://openalex.org/W2159591770","https://openalex.org/W2289985966","https://openalex.org/W2734864502","https://openalex.org/W6605093602"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W66821593","https://openalex.org/W2051274299","https://openalex.org/W2149220986","https://openalex.org/W1521299571","https://openalex.org/W1493012537","https://openalex.org/W468945283","https://openalex.org/W4247736853","https://openalex.org/W2144470400","https://openalex.org/W2911612049"],"abstract_inverted_index":{"Recently,":[0],"the":[1,6,10,21,27,41,44,55,81,89,99,103,114,117,137,142],"speaker":[2,29,66,145],"clustering":[3,56,67,146,151],"approach":[4,68],"exploiting":[5],"intra-conversation":[7,35,82,100],"variability":[8,12,22,74,84,93],"in":[9,23,148],"total":[11,73,83],"space":[13,85],"has":[14],"shown":[15],"promising":[16],"performance.":[17,57],"However,":[18],"there":[19],"exists":[20],"different":[24],"segments":[25,106],"of":[26,43,49,116,150],"same":[28],"within":[30],"a":[31,64],"conversation,":[32],"termed":[33],"as":[34],"intra-speaker":[36,92,101],"variability,":[37,102],"which":[38],"may":[39],"scatter":[40],"distribution":[42],"corresponding":[45],"i-vector":[46],"based":[47,69],"representation":[48],"short":[50,104],"speech":[51,105],"segment,":[52],"and":[53,91],"degrades":[54],"To":[58,112],"address":[59],"this":[60],"issue,":[61],"we":[62,120],"propose":[63],"new":[65],"on":[70,124],"an":[71],"extended":[72],"factor":[75],"analysis.":[76],"In":[77],"our":[78],"proposed":[79,118,138],"method,":[80,119],"is":[86],"divided":[87],"into":[88],"inter-speaker":[90],"space.":[94],"And":[95],"by":[96],"explicitly":[97],"compensating":[98],"would":[107],"be":[108],"represented":[109],"more":[110],"accurately.":[111],"evaluate":[113],"effectiveness":[115],"conduct":[121],"extensive":[122],"experiments":[123],"NIST":[125],"SRE":[126],"2008":[127],"summed":[128],"channel":[129],"telephone":[130],"dataset.":[131],"The":[132],"experimental":[133],"results":[134],"show":[135],"that":[136],"method":[139],"clearly":[140],"outperforms":[141],"other":[143],"state-of-the-art":[144],"techniques":[147],"terms":[149],"error":[152],"rate.":[153]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
