5 search results - page 1 / 1 » Multiple kernel learning for speaker verification |
ICASSP
2008
IEEE
13 years 11 months ago
2008
IEEE
Many speaker verification (SV) systems combine multiple classifiers using score-fusion to improve system performance. For SVM classifiers, an alternative strategy is to combine...
ICASSP
2011
IEEE
12 years 8 months ago
2011
IEEE
We applied a multiple kernel learning (MKL) method based on information-theoretic optimization to speaker recognition. Most of the kernel methods applied to speaker recognition sy...
ICPR
2006
IEEE
14 years 6 months ago
2006
IEEE
Real-word applications often involve a binary hypothesis testing problem with one of the two hypotheses ill-defined and hard to be characterized precisely by a single measure. In ...
ICASSP
2011
IEEE
12 years 8 months ago
2011
IEEE
Recently, Multiple Background Models (M-BMs) [1, 2] have been shown to be useful in speaker verification, where the M-BMs are formed based on different Vocal Tract Lengths (VTLs)...
CSEE
2010
Springer
13 years 2 months ago
2010
Springer
This paper shares the experiences and lessons learned from conducting an NSF-sponsored eight-week summer research program for ten undergraduate students from multiple universities...