Sciweavers

ICASSP
2008
IEEE

Nonparametric feature normalization for SVM-based speaker verification

14 years 4 months ago
Nonparametric feature normalization for SVM-based speaker verification
We investigate several feature normalization and scaling approaches for use in speaker verification based on support vector machines. We are particularly interested in methods that are “knowledge-free” and work for a variety of features, leading us to investigate MLLR transforms, phone N-grams, prosodic sequences, and word N-gram features. Normalization methods studied include mean/variance normalization, TFLLR and TFLOG scaling, and a simple nonparametric approach: rank-normalization. We find that rank-normalization is uniformly competitive with other methods, and improves upon them in many cases.
Andreas Stolcke, Sachin S. Kajarekar, Luciana Ferr
Added 30 May 2010
Updated 30 May 2010
Type Conference
Year 2008
Where ICASSP
Authors Andreas Stolcke, Sachin S. Kajarekar, Luciana Ferrer
Comments (0)