{"id":"https://openalex.org/W1946791388","doi":"https://doi.org/10.1186/s13636-015-0061-x","title":"An improved i-vector extraction algorithm for speaker verification","display_name":"An improved i-vector extraction algorithm for speaker verification","publication_year":2015,"publication_date":"2015-06-26","ids":{"openalex":"https://openalex.org/W1946791388","doi":"https://doi.org/10.1186/s13636-015-0061-x","mag":"1946791388"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-015-0061-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-015-0061-x","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-015-0061-x","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-015-0061-x","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100318020","display_name":"Wei Li","orcid":"https://orcid.org/0000-0001-7824-4839"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Li","raw_affiliation_strings":["Department of Electronic Engineering, Shanghai Jiao Tong University, 800 Dong Chuan Rd, Shanghai, 200240, China","Department of Electronic Engineering, Shanghai Jiao-Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Shanghai Jiao Tong University, 800 Dong Chuan Rd, Shanghai, 200240, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Electronic Engineering, Shanghai Jiao-Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003226543","display_name":"Tianfan Fu","orcid":"https://orcid.org/0000-0002-5574-2541"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianfan Fu","raw_affiliation_strings":["Department of Computer Science and Engineering (CSE), Shanghai Jiao Tong University, 800 Dong Chuan Rd, Shanghai, 200240, China","Department of Computer Science and Engineering (CSE), Shanghai Jiao Tong University, Shanghai, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering (CSE), Shanghai Jiao Tong University, 800 Dong Chuan Rd, Shanghai, 200240, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering (CSE), Shanghai Jiao Tong University, Shanghai, China#TAB#","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036446909","display_name":"Jie Zhu","orcid":"https://orcid.org/0000-0003-2133-4651"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhu","raw_affiliation_strings":["Department of Electronic Engineering, Shanghai Jiao Tong University, 800 Dong Chuan Rd, Shanghai, 200240, China","Department of Electronic Engineering, Shanghai Jiao-Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Shanghai Jiao Tong University, 800 Dong Chuan Rd, Shanghai, 200240, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Electronic Engineering, Shanghai Jiao-Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100318020"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":1.3354,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.85895216,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"2015","issue":"1","first_page":null,"last_page":null},"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":0.9854000210762024,"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/nist","display_name":"NIST","score":0.8394495844841003},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.645808219909668},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6144161224365234},{"id":"https://openalex.org/keywords/covariance-matrix","display_name":"Covariance matrix","score":0.6066345572471619},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.5989663600921631},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5223389863967896},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4987368583679199},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4928136169910431},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4822724461555481},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4487272799015045},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4319150447845459},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37004485726356506},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3122254014015198},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28451740741729736}],"concepts":[{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.8394495844841003},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.645808219909668},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6144161224365234},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.6066345572471619},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.5989663600921631},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5223389863967896},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4987368583679199},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4928136169910431},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4822724461555481},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4487272799015045},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4319150447845459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37004485726356506},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3122254014015198},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28451740741729736},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1186/s13636-015-0061-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-015-0061-x","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-015-0061-x","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1186/s13636-015-0061-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-015-0061-x","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-015-0061-x","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7900000214576721}],"awards":[{"id":"https://openalex.org/G4187866265","display_name":null,"funder_award_id":"6137114","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4668038911","display_name":null,"funder_award_id":"61371147","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1946791388.pdf","grobid_xml":"https://content.openalex.org/works/W1946791388.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W125509687","https://openalex.org/W182365161","https://openalex.org/W204053250","https://openalex.org/W2041823554","https://openalex.org/W2107638917","https://openalex.org/W2121415728","https://openalex.org/W2136879537","https://openalex.org/W2150769028","https://openalex.org/W2167598627","https://openalex.org/W2395069802","https://openalex.org/W2402072010","https://openalex.org/W2404921859","https://openalex.org/W2406312423","https://openalex.org/W4247403446","https://openalex.org/W4298164478"],"related_works":["https://openalex.org/W2134501921","https://openalex.org/W29922783","https://openalex.org/W2094356263","https://openalex.org/W1530471483","https://openalex.org/W1955177963","https://openalex.org/W2594231800","https://openalex.org/W1504805125","https://openalex.org/W1946791388","https://openalex.org/W2596677785","https://openalex.org/W2071159970"],"abstract_inverted_index":{"Over":[0],"recent":[1],"years,":[2],"i-vector-based":[3,215],"framework":[4],"has":[5],"been":[6],"proven":[7],"to":[8,65,76,125,154,210],"provide":[9],"state-of-the-art":[10],"performance":[11],"in":[12,38,130,160],"speaker":[13],"verification.":[14],"Each":[15],"utterance":[16],"is":[17,25,100,106,121,207],"projected":[18],"onto":[19],"a":[20,28,115,123,133],"total":[21,140,162],"factor":[22,116,141,163],"space":[23],"and":[24,60,75,87,193],"represented":[26],"by":[27,72,109,189],"low-dimensional":[29,40],"feature":[30,41],"vector.":[31],"Channel":[32],"compensation":[33,46],"techniques":[34,47],"are":[35,95],"carried":[36],"out":[37],"this":[39,131],"space.":[42,164],"Most":[43],"of":[44,51,157,173,177,197,213],"the":[45,49,67,78,83,139,161,169,174,178,194,198,211],"take":[48],"sets":[50],"extracted":[52],"i-vectors":[53],"as":[54,114],"input.":[55],"By":[56],"constructing":[57],"between-class":[58,68],"covariance":[59],"within-class":[61],"covariance,":[62],"we":[63,144],"attempt":[64],"minimize":[66],"variance":[69,79],"mainly":[70],"caused":[71,108],"channel":[73,110],"effect":[74],"maximize":[77],"between":[80],"speakers.":[81],"In":[82],"real-world":[84],"application,":[85],"enrollment":[86],"test":[88],"data":[89],"from":[90,138],"each":[91],"user":[92],"(or":[93],"speaker)":[94],"always":[96],"scarce.":[97],"Although":[98],"it":[99],"widely":[101],"thought":[102],"that":[103,117],"session":[104,119,158],"variability":[105,159],"mostly":[107],"effects,":[111],"phonetic":[112],"variability,":[113,120],"causes":[118],"still":[122],"matter":[124],"be":[126],"considered.":[127],"We":[128,165],"propose":[129],"paper":[132],"new":[134,151],"i-vector":[135],"extraction":[136],"algorithm":[137,152],"matrix":[142],"which":[143],"term":[145],"component":[146],"reduction":[147],"analysis":[148],"(CRA).":[149],"This":[150],"contributes":[153],"better":[155],"modelling":[156],"reported":[166],"results":[167],"on":[168],"male":[170],"English":[171],"trials":[172],"core":[175],"condition":[176],"NIST":[179,199],"2008":[180],"Speaker":[181],"Recognition":[182],"Evaluation":[183],"(SREs)":[184],"dataset.":[185],"As":[186],"measured":[187],"both":[188],"equal":[190],"error":[191],"rate":[192],"minimum":[195],"values":[196],"detection":[200],"cost":[201],"function,":[202],"10\u201315":[203],"%":[204],"relative":[205],"improvement":[206],"achieved":[208],"compared":[209],"baseline":[212],"traditional":[214],"system.":[216]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}