{"id":"https://openalex.org/W3119029376","doi":"https://doi.org/10.1109/siu49456.2020.9302162","title":"Speaker Diarization using Embedding Vectors","display_name":"Speaker Diarization using Embedding Vectors","publication_year":2020,"publication_date":"2020-10-05","ids":{"openalex":"https://openalex.org/W3119029376","doi":"https://doi.org/10.1109/siu49456.2020.9302162","mag":"3119029376"},"language":"en","primary_location":{"id":"doi:10.1109/siu49456.2020.9302162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/siu49456.2020.9302162","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","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/A5022941579","display_name":"Mesut Toruk","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mesut Toruk","raw_affiliation_strings":["Konuşma ve Dil İşleme Sistemleri,Kocaeli,Türkiye,41470"],"affiliations":[{"raw_affiliation_string":"Konuşma ve Dil İşleme Sistemleri,Kocaeli,Türkiye,41470","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082045666","display_name":"G\u00f6khan Bilgin","orcid":"https://orcid.org/0000-0002-5532-477X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gokhan Bilgin","raw_affiliation_strings":["Yıldız Teknik Üniversitesi,Bilgisayar M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc,İstanbul,Türkiye,34220"],"affiliations":[{"raw_affiliation_string":"Yıldız Teknik Üniversitesi,Bilgisayar M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc,İstanbul,Türkiye,34220","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041471692","display_name":"Ahmet Serbes","orcid":"https://orcid.org/0000-0003-4658-928X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmet Serbes","raw_affiliation_strings":["Yıldız Teknik Üniversitesi,Elektronik-Haberle\u015fme M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc,İstanbul,Türkiye,34220"],"affiliations":[{"raw_affiliation_string":"Yıldız Teknik Üniversitesi,Elektronik-Haberle\u015fme M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc,İstanbul,Türkiye,34220","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5022941579"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2651,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65193366,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"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":0.9970999956130981,"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":0.9955999851226807,"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":0.940287709236145},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7299737930297852},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6836659908294678},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6443037986755371},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5771756172180176},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4696846306324005},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4668821692466736},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.44102850556373596},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.44021591544151306},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.42765161395072937},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.41375842690467834},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0945647656917572}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.940287709236145},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7299737930297852},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6836659908294678},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6443037986755371},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5771756172180176},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4696846306324005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4668821692466736},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44102850556373596},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.44021591544151306},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.42765161395072937},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.41375842690467834},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0945647656917572},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/siu49456.2020.9302162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/siu49456.2020.9302162","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","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":15,"referenced_works":["https://openalex.org/W1589137271","https://openalex.org/W1606894530","https://openalex.org/W1965819578","https://openalex.org/W1990942610","https://openalex.org/W2038101708","https://openalex.org/W2093499222","https://openalex.org/W2125642021","https://openalex.org/W2150769028","https://openalex.org/W2508048623","https://openalex.org/W2514794854","https://openalex.org/W2638067502","https://openalex.org/W2696967604","https://openalex.org/W2890964092","https://openalex.org/W2963470929","https://openalex.org/W2997337336"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"In":[0,67],"recent":[1],"years,":[2],"with":[3,89,107],"the":[4,20,30,49,55,62,65,103,111,120,127,130,136],"rapid":[5],"increase":[6],"of":[7,22,26,110,113,122,129,138],"voice":[8],"data,":[9],"solutions":[10,28],"are":[11,75],"being":[12],"sought":[13],"extensively":[14],"for":[15,77,84],"examination":[16],"and":[17,60,97],"indexing":[18],"in":[19,135],"field":[21],"speech":[23,38,50,56],"processing.":[24],"One":[25],"these":[27,114],"is":[29,34,87,105,133],"speaker":[31,44,78,85],"diarization,":[32],"which":[33],"used":[35,76],"to":[36],"examine":[37],"records":[39],"that":[40],"include":[41],"multi-speaker.":[42],"The":[43,80],"diarization":[45,131],"system":[46,104,132],"basically":[47],"splits":[48],"file":[51],"into":[52],"segments":[53],"using":[54,92,100],"file's":[57],"silence":[58],"fields":[59],"examines":[61],"similarity":[63],"between":[64],"segments.":[66],"this":[68,139],"study,":[69],"deep":[70,94],"learning":[71],"based":[72],"embedding":[73,82,124],"vectors":[74,125],"representation.":[79],"vector":[81],"proposed":[83],"representation":[86],"performed":[88],"x-vectors":[90],"extracted":[91,99],"time-delayed":[93],"neural":[95],"network":[96],"d-vectors":[98],"LSTM.":[101],"Then":[102],"tested":[106],"xd-vectors":[108],"consisting":[109],"combination":[112],"two":[115],"vectors.":[116],"As":[117],"a":[118],"result,":[119],"effect":[121],"representative":[123],"on":[126],"performance":[128],"examined":[134],"scope":[137],"paper.":[140]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}