Matches in SemOpenAlex for { <https://semopenalex.org/work/W2155680790> ?p ?o ?g. }
- W2155680790 endingPage "853" @default.
- W2155680790 startingPage "848" @default.
- W2155680790 abstract "In large population speaker identification (SI) systems, likelihood computations between an unknown speaker's feature vectors and the registered speaker models can be very time-consuming and impose a bottleneck. For applications requiring fast SI, this is a recognized problem and improvements in efficiency would be beneficial. In this paper, we propose a method whereby GMM-based speaker models are clustered using a simple <i xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>k</i> -means algorithm. Then, during the test stage, only a small proportion of speaker models in selected clusters are used in the likelihood computations resulting in a significant speed-up with little to no loss in accuracy. In general, as the number of selected clusters is reduced, the identification accuracy decreases; however, this loss can be controlled through proper tradeoff. The proposed method may also be combined with other test stage speed-up techniques resulting in even greater speed-up gains without additional sacrifices in accuracy." @default.
- W2155680790 created "2016-06-24" @default.
- W2155680790 creator A5030748919 @default.
- W2155680790 creator A5075101547 @default.
- W2155680790 date "2009-05-01" @default.
- W2155680790 modified "2023-09-25" @default.
- W2155680790 title "Speaker Model Clustering for Efficient Speaker Identification in Large Population Applications" @default.
- W2155680790 cites W12737881 @default.
- W2155680790 cites W1975830550 @default.
- W2155680790 cites W1990291240 @default.
- W2155680790 cites W2001918492 @default.
- W2155680790 cites W2041823554 @default.
- W2155680790 cites W2052440526 @default.
- W2155680790 cites W2099124598 @default.
- W2155680790 cites W2108898494 @default.
- W2155680790 cites W2123158946 @default.
- W2155680790 cites W2127914268 @default.
- W2155680790 cites W2128484087 @default.
- W2155680790 cites W2141262306 @default.
- W2155680790 cites W2141934504 @default.
- W2155680790 cites W2144760012 @default.
- W2155680790 cites W2152402526 @default.
- W2155680790 cites W2162416585 @default.
- W2155680790 cites W2162501025 @default.
- W2155680790 cites W2165880886 @default.
- W2155680790 cites W2406898624 @default.
- W2155680790 cites W2545131480 @default.
- W2155680790 cites W42176576 @default.
- W2155680790 doi "https://doi.org/10.1109/tasl.2008.2010882" @default.
- W2155680790 hasPublicationYear "2009" @default.
- W2155680790 type Work @default.
- W2155680790 sameAs 2155680790 @default.
- W2155680790 citedByCount "47" @default.
- W2155680790 countsByYear W21556807902012 @default.
- W2155680790 countsByYear W21556807902013 @default.
- W2155680790 countsByYear W21556807902014 @default.
- W2155680790 countsByYear W21556807902015 @default.
- W2155680790 countsByYear W21556807902016 @default.
- W2155680790 countsByYear W21556807902017 @default.
- W2155680790 countsByYear W21556807902018 @default.
- W2155680790 countsByYear W21556807902019 @default.
- W2155680790 countsByYear W21556807902020 @default.
- W2155680790 countsByYear W21556807902021 @default.
- W2155680790 countsByYear W21556807902022 @default.
- W2155680790 crossrefType "journal-article" @default.
- W2155680790 hasAuthorship W2155680790A5030748919 @default.
- W2155680790 hasAuthorship W2155680790A5075101547 @default.
- W2155680790 hasConcept C11413529 @default.
- W2155680790 hasConcept C116834253 @default.
- W2155680790 hasConcept C133892786 @default.
- W2155680790 hasConcept C138885662 @default.
- W2155680790 hasConcept C144024400 @default.
- W2155680790 hasConcept C149635348 @default.
- W2155680790 hasConcept C149923435 @default.
- W2155680790 hasConcept C153180895 @default.
- W2155680790 hasConcept C154945302 @default.
- W2155680790 hasConcept C2776401178 @default.
- W2155680790 hasConcept C2780513914 @default.
- W2155680790 hasConcept C28490314 @default.
- W2155680790 hasConcept C2908647359 @default.
- W2155680790 hasConcept C2982762665 @default.
- W2155680790 hasConcept C2986627078 @default.
- W2155680790 hasConcept C41008148 @default.
- W2155680790 hasConcept C41895202 @default.
- W2155680790 hasConcept C45374587 @default.
- W2155680790 hasConcept C59822182 @default.
- W2155680790 hasConcept C73555534 @default.
- W2155680790 hasConcept C86803240 @default.
- W2155680790 hasConceptScore W2155680790C11413529 @default.
- W2155680790 hasConceptScore W2155680790C116834253 @default.
- W2155680790 hasConceptScore W2155680790C133892786 @default.
- W2155680790 hasConceptScore W2155680790C138885662 @default.
- W2155680790 hasConceptScore W2155680790C144024400 @default.
- W2155680790 hasConceptScore W2155680790C149635348 @default.
- W2155680790 hasConceptScore W2155680790C149923435 @default.
- W2155680790 hasConceptScore W2155680790C153180895 @default.
- W2155680790 hasConceptScore W2155680790C154945302 @default.
- W2155680790 hasConceptScore W2155680790C2776401178 @default.
- W2155680790 hasConceptScore W2155680790C2780513914 @default.
- W2155680790 hasConceptScore W2155680790C28490314 @default.
- W2155680790 hasConceptScore W2155680790C2908647359 @default.
- W2155680790 hasConceptScore W2155680790C2982762665 @default.
- W2155680790 hasConceptScore W2155680790C2986627078 @default.
- W2155680790 hasConceptScore W2155680790C41008148 @default.
- W2155680790 hasConceptScore W2155680790C41895202 @default.
- W2155680790 hasConceptScore W2155680790C45374587 @default.
- W2155680790 hasConceptScore W2155680790C59822182 @default.
- W2155680790 hasConceptScore W2155680790C73555534 @default.
- W2155680790 hasConceptScore W2155680790C86803240 @default.
- W2155680790 hasIssue "4" @default.
- W2155680790 hasLocation W21556807901 @default.
- W2155680790 hasOpenAccess W2155680790 @default.
- W2155680790 hasPrimaryLocation W21556807901 @default.
- W2155680790 hasRelatedWork W1521049138 @default.
- W2155680790 hasRelatedWork W2129993754 @default.
- W2155680790 hasRelatedWork W2140022733 @default.
- W2155680790 hasRelatedWork W2311320629 @default.
- W2155680790 hasRelatedWork W2370679465 @default.