Matches in SemOpenAlex for { <https://semopenalex.org/work/W2134706965> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W2134706965 endingPage "101" @default.
- W2134706965 startingPage "93" @default.
- W2134706965 abstract "The availability of multiple utterances (and hence, i-vectors) for speaker enrollment brings up several alternatives for their utilization with probabilistic linear discriminant analysis (PLDA). This paper provides an overview of their effective utilization, from a practical viewpoint. We derive expressions for the evaluation of the likelihood ratio for the multi-enrollment case, with details on the computation of the required matrix inversions and determinants. The performance of five different scoring methods, and the effect of i-vector length normalization is compared experimentally. We conclude that length normalization is a useful technique for all but one of the scoring methods considered, and averaging i-vectors is the most effective out of the methods compared. We also study the application of multicondition training on the PLDA model. Our experiments indicate that multicondition training is more effective in estimating PLDA hyperparameters than it is for likelihood computation. Finally, we look at the effect of the configuration of the enrollment data on PLDA scoring, studying the properties of conditional dependence and number-of-enrollment-utterances per target speaker. Our experiments indicate that these properties affect the performance of the PLDA model. These results further support the conclusion that i-vector averaging is a simple and effective way to process multiple enrollment utterances." @default.
- W2134706965 created "2016-06-24" @default.
- W2134706965 creator A5000473932 @default.
- W2134706965 creator A5037259225 @default.
- W2134706965 creator A5043168931 @default.
- W2134706965 creator A5078300199 @default.
- W2134706965 date "2014-08-01" @default.
- W2134706965 modified "2023-09-26" @default.
- W2134706965 title "From single to multiple enrollment i-vectors: Practical PLDA scoring variants for speaker verification" @default.
- W2134706965 cites W1990942610 @default.
- W2134706965 cites W2088127636 @default.
- W2134706965 cites W2121061347 @default.
- W2134706965 cites W2150769028 @default.
- W2134706965 cites W2166469867 @default.
- W2134706965 doi "https://doi.org/10.1016/j.dsp.2014.05.001" @default.
- W2134706965 hasPublicationYear "2014" @default.
- W2134706965 type Work @default.
- W2134706965 sameAs 2134706965 @default.
- W2134706965 citedByCount "52" @default.
- W2134706965 countsByYear W21347069652014 @default.
- W2134706965 countsByYear W21347069652015 @default.
- W2134706965 countsByYear W21347069652016 @default.
- W2134706965 countsByYear W21347069652017 @default.
- W2134706965 countsByYear W21347069652018 @default.
- W2134706965 countsByYear W21347069652019 @default.
- W2134706965 countsByYear W21347069652020 @default.
- W2134706965 countsByYear W21347069652021 @default.
- W2134706965 countsByYear W21347069652022 @default.
- W2134706965 countsByYear W21347069652023 @default.
- W2134706965 crossrefType "journal-article" @default.
- W2134706965 hasAuthorship W2134706965A5000473932 @default.
- W2134706965 hasAuthorship W2134706965A5037259225 @default.
- W2134706965 hasAuthorship W2134706965A5043168931 @default.
- W2134706965 hasAuthorship W2134706965A5078300199 @default.
- W2134706965 hasConcept C11413529 @default.
- W2134706965 hasConcept C133892786 @default.
- W2134706965 hasConcept C136886441 @default.
- W2134706965 hasConcept C144024400 @default.
- W2134706965 hasConcept C153180895 @default.
- W2134706965 hasConcept C154945302 @default.
- W2134706965 hasConcept C19165224 @default.
- W2134706965 hasConcept C28490314 @default.
- W2134706965 hasConcept C2982762665 @default.
- W2134706965 hasConcept C41008148 @default.
- W2134706965 hasConcept C45374587 @default.
- W2134706965 hasConcept C49937458 @default.
- W2134706965 hasConcept C8642999 @default.
- W2134706965 hasConceptScore W2134706965C11413529 @default.
- W2134706965 hasConceptScore W2134706965C133892786 @default.
- W2134706965 hasConceptScore W2134706965C136886441 @default.
- W2134706965 hasConceptScore W2134706965C144024400 @default.
- W2134706965 hasConceptScore W2134706965C153180895 @default.
- W2134706965 hasConceptScore W2134706965C154945302 @default.
- W2134706965 hasConceptScore W2134706965C19165224 @default.
- W2134706965 hasConceptScore W2134706965C28490314 @default.
- W2134706965 hasConceptScore W2134706965C2982762665 @default.
- W2134706965 hasConceptScore W2134706965C41008148 @default.
- W2134706965 hasConceptScore W2134706965C45374587 @default.
- W2134706965 hasConceptScore W2134706965C49937458 @default.
- W2134706965 hasConceptScore W2134706965C8642999 @default.
- W2134706965 hasLocation W21347069651 @default.
- W2134706965 hasOpenAccess W2134706965 @default.
- W2134706965 hasPrimaryLocation W21347069651 @default.
- W2134706965 hasRelatedWork W1863050261 @default.
- W2134706965 hasRelatedWork W1991269640 @default.
- W2134706965 hasRelatedWork W2016839265 @default.
- W2134706965 hasRelatedWork W2018445155 @default.
- W2134706965 hasRelatedWork W2023847438 @default.
- W2134706965 hasRelatedWork W2118511662 @default.
- W2134706965 hasRelatedWork W2147493033 @default.
- W2134706965 hasRelatedWork W2946038180 @default.
- W2134706965 hasRelatedWork W3143036988 @default.
- W2134706965 hasRelatedWork W2508457823 @default.
- W2134706965 hasVolume "31" @default.
- W2134706965 isParatext "false" @default.
- W2134706965 isRetracted "false" @default.
- W2134706965 magId "2134706965" @default.
- W2134706965 workType "article" @default.