{"id":"https://openalex.org/W2111954936","doi":"https://doi.org/10.1109/icassp.2009.4960514","title":"Maximum margin linear kernel optimization for speaker verification","display_name":"Maximum margin linear kernel optimization for speaker verification","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2111954936","doi":"https://doi.org/10.1109/icassp.2009.4960514","mag":"2111954936"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960514","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960514","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal 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/A5113697338","display_name":"Mohamed Kamal Omar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohamed Kamal Omar","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029030495","display_name":"Jason Pelecanos","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Pelecanos","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111944718","display_name":"Ganesh N. Ramaswamy","orcid":"https://orcid.org/0009-0002-8015-0844"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ganesh N. Ramaswamy","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9059,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.81228619,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4037","last_page":"4040"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9922000169754028,"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":0.9704999923706055,"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/discriminative-model","display_name":"Discriminative model","score":0.7296183705329895},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6664011478424072},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6492989659309387},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6152598857879639},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5984006524085999},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.583389937877655},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5823423862457275},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5562788248062134},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5532575845718384},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5121018886566162},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5002124309539795},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.457223117351532},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.4194410443305969},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.41911524534225464},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4140126705169678},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3087916374206543},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21113011240959167},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.18922650814056396}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7296183705329895},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6664011478424072},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6492989659309387},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6152598857879639},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5984006524085999},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.583389937877655},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5823423862457275},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5562788248062134},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5532575845718384},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5121018886566162},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5002124309539795},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.457223117351532},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.4194410443305969},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.41911524534225464},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4140126705169678},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3087916374206543},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21113011240959167},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.18922650814056396},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2009.4960514","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960514","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.997.9336","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.997.9336","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mirlab.org/conference_papers/International_Conference/ICASSP%202009/pdfs/0004037.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W204053250","https://openalex.org/W1916834241","https://openalex.org/W1999613943","https://openalex.org/W2041823554","https://openalex.org/W2078953162","https://openalex.org/W2105393821","https://openalex.org/W2144760012","https://openalex.org/W2148554390","https://openalex.org/W2148603752","https://openalex.org/W2397634864","https://openalex.org/W6608353291","https://openalex.org/W6640010188","https://openalex.org/W6675661078","https://openalex.org/W6712325649"],"related_works":["https://openalex.org/W2118039276","https://openalex.org/W2051274299","https://openalex.org/W1197719229","https://openalex.org/W468945283","https://openalex.org/W2381158726","https://openalex.org/W4235705411","https://openalex.org/W1992796048","https://openalex.org/W1521299571","https://openalex.org/W2316548414","https://openalex.org/W1516392727"],"abstract_inverted_index":{"This":[0,17,54,77],"paper":[1],"describes":[2],"a":[3,85,130,142,156,175],"novel":[4],"approach":[5,18,55,78,113,171],"for":[6,26,36,59],"discriminative":[7],"modeling":[8],"and":[9,35,58,102,141,162],"its":[10],"application":[11],"to":[12,31,41,64,88,93,114,122],"automatic":[13],"text-independent":[14],"speaker":[15,34,57,118],"verification.":[16],"maximizes":[19,51,74],"the":[20,23,32,98,115,123,135],"margin":[21],"between":[22,90],"model":[24,126],"scores":[25,91],"pairs":[27,37,60,94],"of":[28,38,61,95,97,104,174],"utterances":[29,39,62,96],"belonging":[30,40,63,92],"same":[33,99],"different":[42,65,105],"speakers.":[43,66,106],"A":[44,67],"low-dimensional":[45,68],"linear":[46,69],"kernel":[47,70,183],"is":[48,71],"estimated":[49,72],"which":[50,73,81,83],"this":[52,75,108,112],"margin.":[53,76],"emphasizes":[56,79],"features":[80,82],"have":[84],"better":[86],"ability":[87],"discriminate":[89],"target":[100],"speakers":[101],"those":[103],"In":[107],"paper,":[109],"we":[110],"apply":[111],"NIST":[116],"2005":[117],"verification":[119],"task.":[120],"Compared":[121],"Gaussian":[124],"mixture":[125],"(GMM)":[127],"baseline":[128,184],"system,":[129],"17.7%":[131],"relative":[132,144,158,164],"improvement":[133,145,159,165],"in":[134,146,160,166],"minimum":[136],"detection":[137],"cost":[138],"function":[139],"(DCF)":[140],"11.7%":[143],"equal":[147],"error":[148],"rate":[149],"(EER)":[150],"are":[151],"obtained.":[152],"We":[153],"achieve":[154],"also":[155],"5.7%":[157],"EER":[161],"2.3%":[163],"DCF":[167],"by":[168],"using":[169],"our":[170],"on":[172],"top":[173],"nuisance":[176],"attribute":[177],"projection":[178],"(NAP)":[179],"compensated":[180],"GMM":[181],"based":[182],"system.":[185]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}