{"id":"https://openalex.org/W2395747372","doi":"https://doi.org/10.21437/interspeech.2011-146","title":"Addressing the data-imbalance problem in kernel-based speaker verification via utterance partitioning and speaker comparison","display_name":"Addressing the data-imbalance problem in kernel-based speaker verification via utterance partitioning and speaker comparison","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2395747372","doi":"https://doi.org/10.21437/interspeech.2011-146","mag":"2395747372"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-146","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Rao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5068768998","display_name":"Man\u2010Wai Mak","orcid":"https://orcid.org/0000-0001-8854-3760"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Man-Wai Mak","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6379,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.91324994,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2717","last_page":"2720"},"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":0.9940000176429749,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9878000020980835,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7879303693771362},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.683783769607544},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.679900586605072},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6694794297218323},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6512485146522522},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6481763124465942},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6230467557907104},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5983894467353821},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.5837864875793457},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5697937607765198},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.4749757647514343},{"id":"https://openalex.org/keywords/radial-basis-function-kernel","display_name":"Radial basis function kernel","score":0.44936031103134155},{"id":"https://openalex.org/keywords/kernel-method","display_name":"Kernel method","score":0.3113822937011719},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19933828711509705}],"concepts":[{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7879303693771362},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.683783769607544},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.679900586605072},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6694794297218323},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6512485146522522},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6481763124465942},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6230467557907104},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5983894467353821},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.5837864875793457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5697937607765198},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.4749757647514343},{"id":"https://openalex.org/C75866337","wikidata":"https://www.wikidata.org/wiki/Q7280263","display_name":"Radial basis function kernel","level":4,"score":0.44936031103134155},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.3113822937011719},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19933828711509705},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2011-146","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.221.6587","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.221.6587","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/interspeech11b.pdf","raw_type":"text"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/44462","is_oa":false,"landing_page_url":"http://hdl.handle.net/10397/44462","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","display_name":"Reduced inequalities","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W148257761","https://openalex.org/W2035732044","https://openalex.org/W2041823554","https://openalex.org/W2078953162","https://openalex.org/W2109781262","https://openalex.org/W2121890799","https://openalex.org/W2136879537","https://openalex.org/W2144760012","https://openalex.org/W2149338142","https://openalex.org/W2397634864","https://openalex.org/W3120116802"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","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":{"GMM-SVM":[0,130],"has":[1],"become":[2],"a":[3,11],"promising":[4],"approach":[5,16],"to":[6,135],"textindependent":[7],"speaker":[8,67,136,151,155,158],"verification.":[9],"However,":[10],"problematic":[12],"issue":[13],"of":[14,25,98],"this":[15],"is":[17,133,143],"the":[18,23,33,62,79,88,96,104,122,140,147],"extremely":[19],"serious":[20],"imbalance":[21],"between":[22,78,90],"numbers":[24],"speaker-class":[26,46],"and":[27,59,82,94,113,138],"impostor-class":[28],"utterances":[29],"available":[30],"for":[31,48],"training":[32,50,64],"speaker-dependent":[34],"SVMs.":[35],"This":[36,85],"data-imbalance":[37],"problem":[38],"can":[39],"be":[40],"addressed":[41],"by":[42],"(1)":[43],"creating":[44],"more":[45],"supervectors":[47],"SVM":[49,63],"through":[51],"utterance":[52,162],"partitioning":[53],"with":[54,131],"acoustic":[55],"vector":[56],"resampling":[57],"(UP-AVR)":[58],"(2)":[60],"avoiding":[61],"so":[65],"that":[66,129,139],"scores":[68],"are":[69],"formulated":[70],"as":[71],"an":[72],"inner":[73],"product":[74],"discriminant":[75],"function":[76],"(IPDF)":[77],"target-speaker\u2019s":[80],"supervector":[81],"test":[83],"supervector.":[84],"paper":[86],"highlights":[87],"differences":[89],"these":[91],"two":[92],"approaches":[93],"compares":[95],"effect":[97],"using":[99],"different":[100],"kernels":[101],"\u2013":[102,116],"including":[103],"KL":[105,148],"divergence":[106],"kernel,":[107],"GMM-UBM":[108],"mean":[109],"interval":[110],"(GUMI)":[111],"kernel":[112,115,142,149],"geometric-mean-comparison":[114],"on":[117,121],"their":[118],"performance.":[119],"Experiments":[120],"NIST":[123,160],"2010":[124],"Speaker":[125],"Recognition":[126],"Evaluation":[127],"suggest":[128],"UP-AVR":[132],"superior":[134],"comparison":[137],"GUMI":[141],"slightly":[144],"better":[145],"than":[146],"in":[150],"comparison.":[152],"Index":[153],"Terms:":[154],"verification,":[156],"GMM-SVM,":[157],"comparison,":[159],"SRE,":[161],"partitioning,":[163],"data":[164],"imbalance.":[165]},"counts_by_year":[{"year":2020,"cited_by_count":12},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}