{"id":"https://openalex.org/W1965819578","doi":"https://doi.org/10.1109/slt.2014.7078610","title":"Speaker diarization with plda i-vector scoring and unsupervised calibration","display_name":"Speaker diarization with plda i-vector scoring and unsupervised calibration","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W1965819578","doi":"https://doi.org/10.1109/slt.2014.7078610","mag":"1965819578"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2014.7078610","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078610","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","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/A5046596198","display_name":"Gregory Sell","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gregory Sell","raw_affiliation_strings":["Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","Human Language Technol. Center of Excellence Johns, Hopkins Univ., Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Human Language Technol. Center of Excellence Johns, Hopkins Univ., Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000143881","display_name":"Daniel Garcia-Romero","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Garcia-Romero","raw_affiliation_strings":["Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","Human Language Technol. Center of Excellence Johns, Hopkins Univ., Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Human Language Technol. Center of Excellence Johns, Hopkins Univ., Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5046596198"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":10.994,"has_fulltext":false,"cited_by_count":210,"citation_normalized_percentile":{"value":0.98359952,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"413","last_page":"417"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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":0.9973999857902527,"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/computer-science","display_name":"Computer science","score":0.8089478015899658},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.8022481203079224},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6664096117019653},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6469398140907288},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.570378303527832},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5074595808982849},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.4897799491882324},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44097253680229187}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8089478015899658},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8022481203079224},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6664096117019653},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6469398140907288},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.570378303527832},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5074595808982849},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.4897799491882324},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44097253680229187}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2014.7078610","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078610","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2038101708","https://openalex.org/W2046015436","https://openalex.org/W2081074144","https://openalex.org/W2093499222","https://openalex.org/W2101587318","https://openalex.org/W2125642021","https://openalex.org/W2144411866","https://openalex.org/W2150769028","https://openalex.org/W2289985966","https://openalex.org/W2395750323","https://openalex.org/W2400584454","https://openalex.org/W6678433015","https://openalex.org/W6682600690"],"related_works":["https://openalex.org/W4384929466","https://openalex.org/W1521049138","https://openalex.org/W2144208207","https://openalex.org/W1813780412","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2160753975","https://openalex.org/W2118860825","https://openalex.org/W2096510939","https://openalex.org/W2161543916"],"abstract_inverted_index":{"Speaker":[0],"diarization":[1,99,140],"via":[2],"unsupervised":[3,68],"i-vector":[4,55,88],"clustering":[5,77],"has":[6],"gained":[7],"popularity":[8],"in":[9,62,86,97],"recent":[10],"years.":[11],"In":[12,40],"this":[13,41],"approach,":[14],"i-vectors":[15],"are":[16],"extracted":[17],"from":[18,24],"short":[19],"clips":[20],"of":[21,70,120],"speech":[22,110],"segmented":[23],"a":[25,45,57,95,117],"larger":[26],"multi-speaker":[27],"conversation":[28],"and":[29,66,116,122,135],"organized":[30],"into":[31],"speaker":[32,63],"clusters,":[33],"typically":[34],"according":[35],"to":[36,74],"their":[37],"cosine":[38,133],"score.":[39],"paper,":[42],"we":[43,123],"propose":[44],"system":[46,104,131],"that":[47,83,125,136],"incorporates":[48],"probabilistic":[49],"linear":[50],"discriminant":[51],"analysis":[52],"(PLDA)":[53],"for":[54],"scoring,":[56,134],"method":[58],"already":[59],"frequently":[60],"utilized":[61],"recognition":[64],"tasks,":[65],"uses":[67],"calibration":[69],"the":[71,76,87,98,106,129],"PLDA":[72,126],"scores":[73],"determine":[75],"stopping":[78],"criterion.":[79],"We":[80,101],"also":[81],"demonstrate":[82],"denser":[84],"sampling":[85],"space":[89],"with":[90,132],"overlapping":[91,137],"temporal":[92],"segments":[93,138],"provides":[94],"gain":[96],"task.":[100],"test":[102],"our":[103],"on":[105],"CALLHOME":[107],"conversational":[108],"telephone":[109],"corpus,":[111],"which":[112],"includes":[113],"multiple":[114],"languages":[115],"varying":[118],"number":[119],"speakers,":[121],"show":[124],"scoring":[127],"outperforms":[128],"same":[130],"reduce":[139],"error":[141],"rate":[142],"(DER)":[143],"as":[144],"well.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":38},{"year":2019,"cited_by_count":39},{"year":2018,"cited_by_count":20},{"year":2017,"cited_by_count":18},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":2}],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2025-10-10T00:00:00"}