{"id":"https://openalex.org/W2283724112","doi":"https://doi.org/10.1007/s00034-015-0206-2","title":"Improved i-Vector Representation for Speaker Diarization","display_name":"Improved i-Vector Representation for Speaker Diarization","publication_year":2015,"publication_date":"2015-12-22","ids":{"openalex":"https://openalex.org/W2283724112","doi":"https://doi.org/10.1007/s00034-015-0206-2","mag":"2283724112"},"language":"en","primary_location":{"id":"doi:10.1007/s00034-015-0206-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00034-015-0206-2","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs00034-015-0206-2.pdf","source":{"id":"https://openalex.org/S20109229","display_name":"Circuits Systems and Signal Processing","issn_l":"0278-081X","issn":["0278-081X","1531-5878"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320186","host_organization_name":"Birkh\u00e4user","host_organization_lineage":["https://openalex.org/P4310320186","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Birkh\u00e4user","Springer Science+Business Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Circuits, Systems, and Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007%2Fs00034-015-0206-2.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078337531","display_name":"Yan Xu","orcid":"https://orcid.org/0000-0001-6483-4336"},"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 Xu","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, The University of Science and Technology of China, Hefei, People\u2019s Republic of China","National Engineering Laboratory of Speech and Language Information Processing, The University of Science and Technology of China, Hefei, People's Republic of China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, The University of Science and Technology of China, Hefei, People\u2019s Republic of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, The University of Science and Technology of China, Hefei, People's Republic of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000620878","display_name":"Ian McLoughlin","orcid":"https://orcid.org/0000-0001-7111-2008"},"institutions":[{"id":"https://openalex.org/I20581793","display_name":"University of Kent","ror":"https://ror.org/00xkeyj56","country_code":"GB","type":"education","lineage":["https://openalex.org/I20581793"]},{"id":"https://openalex.org/I167056439","display_name":"Medway School of Pharmacy","ror":"https://ror.org/00fa9v295","country_code":"GB","type":"education","lineage":["https://openalex.org/I167056439"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Ian McLoughlin","raw_affiliation_strings":["School of Computing, The University of Kent, Medway Campus, Chatham, UK"],"affiliations":[{"raw_affiliation_string":"School of Computing, The University of Kent, Medway Campus, Chatham, UK","institution_ids":["https://openalex.org/I167056439","https://openalex.org/I20581793"]}]},{"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":["National Engineering Laboratory of Speech and Language Information Processing, The University of Science and Technology of China, Hefei, People\u2019s Republic of China","National Engineering Laboratory of Speech and Language Information Processing, The University of Science and Technology of China, Hefei, People's Republic of China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, The University of Science and Technology of China, Hefei, People\u2019s Republic of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, The University of Science and Technology of China, Hefei, People's Republic of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","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":["National Engineering Laboratory of Speech and Language Information Processing, The University of Science and Technology of China, Hefei, People\u2019s Republic of China","National Engineering Laboratory of Speech and Language Information Processing, The University of Science and Technology of China, Hefei, People's Republic of China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, The University of Science and Technology of China, Hefei, People\u2019s Republic of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, The University of Science and Technology of China, Hefei, People's Republic of China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5000620878"],"corresponding_institution_ids":["https://openalex.org/I167056439","https://openalex.org/I20581793"],"apc_list":null,"apc_paid":null,"fwci":5.3572,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.95908276,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"35","issue":"9","first_page":"3393","last_page":"3404"},"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":0.9991999864578247,"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":0.9983999729156494,"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":0.7576019763946533},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.7283180952072144},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6967368721961975},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.692068338394165},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6644901037216187},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6447794437408447},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5699496269226074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.544979453086853},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5353318452835083},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.48849713802337646},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4814276397228241},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.42698997259140015},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3863150179386139}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7576019763946533},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7283180952072144},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6967368721961975},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.692068338394165},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6644901037216187},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6447794437408447},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5699496269226074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.544979453086853},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5353318452835083},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.48849713802337646},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4814276397228241},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.42698997259140015},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3863150179386139},{"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},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s00034-015-0206-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00034-015-0206-2","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs00034-015-0206-2.pdf","source":{"id":"https://openalex.org/S20109229","display_name":"Circuits Systems and Signal Processing","issn_l":"0278-081X","issn":["0278-081X","1531-5878"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320186","host_organization_name":"Birkh\u00e4user","host_organization_lineage":["https://openalex.org/P4310320186","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Birkh\u00e4user","Springer Science+Business Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Circuits, Systems, and Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:kar.kent.ac.uk:55023","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00034-015-0206-2>)","pdf_url":null,"source":{"id":"https://openalex.org/S4377196264","display_name":"Kent Academic Repository (University of Kent)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20581793","host_organization_name":"University of Kent","host_organization_lineage":["https://openalex.org/I20581793"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":{"id":"doi:10.1007/s00034-015-0206-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00034-015-0206-2","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs00034-015-0206-2.pdf","source":{"id":"https://openalex.org/S20109229","display_name":"Circuits Systems and Signal Processing","issn_l":"0278-081X","issn":["0278-081X","1531-5878"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320186","host_organization_name":"Birkh\u00e4user","host_organization_lineage":["https://openalex.org/P4310320186","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Birkh\u00e4user","Springer Science+Business Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Circuits, Systems, and Signal Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1023919524","display_name":null,"funder_award_id":", Grant","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2376276132","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G352716874","display_name":null,"funder_award_id":"61172158","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5249178904","display_name":null,"funder_award_id":"Grant No. 6","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5616351183","display_name":null,"funder_award_id":"00000","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6833829493","display_name":null,"funder_award_id":"0000000","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G6844051781","display_name":null,"funder_award_id":"00000","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8951484681","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2283724112.pdf","grobid_xml":"https://content.openalex.org/works/W2283724112.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W3765491","https://openalex.org/W1970578576","https://openalex.org/W2040429011","https://openalex.org/W2046899276","https://openalex.org/W2115599677","https://openalex.org/W2125642021","https://openalex.org/W2147768505","https://openalex.org/W2150769028","https://openalex.org/W2153181479","https://openalex.org/W2156255174","https://openalex.org/W2159591770","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2183984815","https://openalex.org/W2289985966","https://openalex.org/W2296295429","https://openalex.org/W2405476549","https://openalex.org/W6600704668","https://openalex.org/W6634782987"],"related_works":["https://openalex.org/W2118039276","https://openalex.org/W1963976507","https://openalex.org/W2048014685","https://openalex.org/W2370972896","https://openalex.org/W2206035908","https://openalex.org/W3119288895","https://openalex.org/W2185075503","https://openalex.org/W1197719229","https://openalex.org/W2381158726","https://openalex.org/W2552734076"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"using":[3,44,62],"a":[4,32,38,45,55,81,122],"previously":[5],"well-trained":[6],"deep":[7],"neural":[8],"network":[9],"(DNN)":[10],"to":[11,30,66,75,97,120,136],"enhance":[12],"the":[13,24,51,60,68,77,99,113,126],"i-vector":[14],"representation":[15],"used":[16,29],"for":[17,105],"speaker":[18,129],"diarization.":[19],"In":[20],"effect,":[21],"we":[22,53,90,111],"replace":[23],"Gaussian":[25],"mixture":[26],"model":[27,35],"typically":[28],"train":[31,50,76],"universal":[33],"background":[34],"(UBM),":[36],"with":[37],"DNN":[39,61,93],"that":[40],"has":[41],"been":[42],"trained":[43],"different":[46],"large-scale":[47],"dataset.":[48],"To":[49],"T-matrix,":[52],"use":[54,92],"supervised":[56],"UBM":[57,78,84],"obtained":[58],"from":[59,86,109],"filterbank":[63],"input":[64],"features":[65,74,96],"calculate":[67,98],"posterior":[69],"information":[70],"and":[71,94,101],"then":[72],"MFCC":[73,95],"instead":[79],"of":[80],"traditional":[82],"unsupervised":[83],"derived":[85],"single":[87],"features.":[88],"Next":[89],"jointly":[91],"zeroth-":[100],"first-order":[102],"Baum\u2013Welch":[103],"statistics":[104],"training":[106],"an":[107],"extractor":[108],"which":[110],"obtain":[112],"i-vector.":[114],"The":[115],"system":[116],"will":[117],"be":[118],"shown":[119],"achieve":[121],"significant":[123],"improvement":[124],"on":[125],"NIST":[127],"2008":[128],"recognition":[130],"evaluation":[131],"telephone":[132],"data":[133],"task":[134],"compared":[135],"state-of-the-art":[137],"approaches.":[138]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}