{"id":"https://openalex.org/W2057712776","doi":"https://doi.org/10.1109/iscslp.2012.6423527","title":"Alleviating the small sample-size problem in i-vector based speaker verification","display_name":"Alleviating the small sample-size problem in i-vector based speaker verification","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2057712776","doi":"https://doi.org/10.1109/iscslp.2012.6423527","mag":"2057712776"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2012.6423527","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2012.6423527","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":"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/A5035226758","display_name":"Wei Rao","orcid":"https://orcid.org/0000-0002-7237-0874"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wei Rao","raw_affiliation_strings":["Department of Electronic and Information Engineering, Hong Kong Polytechnic University, Hong Kong, China","Dept. of Electronic and Information Engineering The Hong Kong Polytechnic University, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic and Information Engineering, Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Dept. of Electronic and Information Engineering The Hong Kong Polytechnic University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068768998","display_name":"Man\u2010Wai Mak","orcid":"https://orcid.org/0000-0001-8854-3760"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Man-Wai Mak","raw_affiliation_strings":["Department of Electronic and Information Engineering, Hong Kong Polytechnic University, Hong Kong, China","Dept. of Electronic and Information Engineering The Hong Kong Polytechnic University, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic and Information Engineering, Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Dept. of Electronic and Information Engineering The Hong Kong Polytechnic University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2384,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.82830582,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"6","issue":null,"first_page":"335","last_page":"339"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","score":0.9944999814033508,"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":0.6752214431762695},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.6007692217826843},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.5995304584503174},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5808907747268677},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5573230385780334},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.5507243871688843},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5009748935699463},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48305636644363403},{"id":"https://openalex.org/keywords/covariance-matrix","display_name":"Covariance matrix","score":0.4753139615058899},{"id":"https://openalex.org/keywords/scatter-matrix","display_name":"Scatter matrix","score":0.45639416575431824},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.4484257996082306},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4393303394317627},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.417250394821167},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25175154209136963},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2456417679786682},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23985445499420166},{"id":"https://openalex.org/keywords/estimation-of-covariance-matrices","display_name":"Estimation of covariance matrices","score":0.09768632054328918}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6752214431762695},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.6007692217826843},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.5995304584503174},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5808907747268677},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5573230385780334},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.5507243871688843},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5009748935699463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48305636644363403},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.4753139615058899},{"id":"https://openalex.org/C176917957","wikidata":"https://www.wikidata.org/wiki/Q7430596","display_name":"Scatter matrix","level":4,"score":0.45639416575431824},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.4484257996082306},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4393303394317627},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.417250394821167},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25175154209136963},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2456417679786682},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23985445499420166},{"id":"https://openalex.org/C180877172","wikidata":"https://www.wikidata.org/wiki/Q5401390","display_name":"Estimation of covariance matrices","level":3,"score":0.09768632054328918},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iscslp.2012.6423527","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2012.6423527","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.303.5580","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.303.5580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.eie.polyu.edu.hk/%7Emwmak/papers/iscslp12.pdf","raw_type":"text"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/50868","is_oa":false,"landing_page_url":"http://hdl.handle.net/10397/50868","pdf_url":null,"source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6899999976158142,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W111477576","https://openalex.org/W126055469","https://openalex.org/W1663973292","https://openalex.org/W1916834241","https://openalex.org/W1999772635","https://openalex.org/W2009086942","https://openalex.org/W2035732044","https://openalex.org/W2046649434","https://openalex.org/W2050693797","https://openalex.org/W2078953162","https://openalex.org/W2088900896","https://openalex.org/W2089322632","https://openalex.org/W2098693229","https://openalex.org/W2107542203","https://openalex.org/W2107638917","https://openalex.org/W2109363337","https://openalex.org/W2121647436","https://openalex.org/W2124112941","https://openalex.org/W2147147599","https://openalex.org/W2150769028","https://openalex.org/W2152939563","https://openalex.org/W2163406054","https://openalex.org/W2397634864","https://openalex.org/W2399224588","https://openalex.org/W2406312423","https://openalex.org/W2407342067","https://openalex.org/W2748151992","https://openalex.org/W3005272312","https://openalex.org/W3016988317","https://openalex.org/W3018586685","https://openalex.org/W4238240379","https://openalex.org/W6604441197","https://openalex.org/W6640010188","https://openalex.org/W6676261310","https://openalex.org/W6682609908","https://openalex.org/W6684134493","https://openalex.org/W6712325649","https://openalex.org/W6713180605","https://openalex.org/W6713727690","https://openalex.org/W6714435555"],"related_works":["https://openalex.org/W181978178","https://openalex.org/W2118039276","https://openalex.org/W2040171177","https://openalex.org/W2109788865","https://openalex.org/W2072065453","https://openalex.org/W2122256703","https://openalex.org/W1972766437","https://openalex.org/W2379352318","https://openalex.org/W2020755204","https://openalex.org/W2151309195"],"abstract_inverted_index":{"This":[0,104],"paper":[1,105],"investigates":[2],"the":[3,20,25,32,37,49,91,117,127,140,146,152,175],"small":[4,112],"sample-size":[5,113],"problem":[6],"in":[7,24,130,155],"i-vector":[8],"based":[9,165],"speaker":[10,39,100,143],"verification":[11],"systems.":[12],"The":[13],"idea":[14],"of":[15,22,27,42,93,97,145],"i-vectors":[16,118,160],"is":[17,45],"to":[18,47,109],"represent":[19],"characteristics":[21],"speakers":[23,78,94],"factors":[26],"a":[28],"factor":[29,33],"analyzer.":[30],"Because":[31],"loading":[34],"matrix":[35,128,153],"defines":[36],"possible":[38],"and":[40,61,142,149,181],"channel-variability":[41],"i-vectors,":[43],"it":[44],"important":[46],"suppress":[48],"unwanted":[50],"channel":[51],"variability.":[52],"Linear":[53],"discriminant":[54],"analysis":[55],"(LDA),":[56],"within-class":[57],"covariance":[58],"normalization":[59],"(WCCN),":[60],"probabilistic":[62],"LDA":[63,123,131,137,156,180],"are":[64,101],"commonly":[65],"used":[66],"for":[67,84],"such":[68],"purpose.":[69],"These":[70],"methods,":[71],"however,":[72],"require":[73],"training":[74,147],"data":[75],"comprising":[76],"many":[77],"each":[79],"providing":[80],"sufficient":[81],"recording":[82],"sessions":[83,98],"good":[85],"performance.":[86],"Performance":[87],"will":[88],"suffer":[89],"when":[90],"number":[92,96],"and/or":[95],"per":[99],"too":[102],"small.":[103],"compares":[106],"four":[107],"approaches":[108],"addressing":[110],"this":[111],"problem:":[114],"(1)":[115],"preprocessing":[116],"by":[119,132,138,157,178],"PCA":[120],"before":[121],"applying":[122,135],"(PCA+LDA),":[124],"(2)":[125],"replacing":[126],"inverse":[129],"pseudo-inverse,":[133],"(3)":[134],"multi-way":[136,179],"exploiting":[139],"microphone":[141],"labels":[144],"data,":[148],"(4)":[150],"increasing":[151],"rank":[154],"generating":[158],"more":[159],"using":[161],"utterance":[162,172],"partitioning.":[163],"Results":[164],"on":[166],"NIST":[167],"2010":[168],"SRE":[169],"suggests":[170],"that":[171],"partitioning":[173],"performs":[174],"best,":[176],"followed":[177],"PCA+LDA.":[182]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":12},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}