Sciweavers

4 search results - page 1 / 1
» Learning vocal tract variables with multi-task kernels
Sort
View
ICASSP
2011
IEEE
12 years 10 months ago
Learning vocal tract variables with multi-task kernels
The problem of acoustic-to-articulatory speech inversion continues to be a challenging research problem which significantly impacts automatic speech recognition robustness and ac...
Hachem Kadri, Emmanuel Duflos, Philippe Preux
COLT
2008
Springer
13 years 8 months ago
Learning Coordinate Gradients with Multi-Task Kernels
Coordinate gradient learning is motivated by the problem of variable selection and determining variable covariation. In this paper we propose a novel unifying framework for coordi...
Yiming Ying, Colin Campbell
CSL
2007
Springer
13 years 7 months ago
Speaker-adaptive learning of resonance targets in a hidden trajectory model of speech coarticulation
A novel speaker-adaptive learning algorithm is developed and evaluated for a hidden trajectory model of speech coarticulation and reduction. Central to this model is the process o...
Dong Yu, Li Deng, Alex Acero
ICASSP
2011
IEEE
12 years 10 months ago
Use of VTL-wise models in feature-mapping framework to achieve performance of multiple-background models in speaker verification
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)...
Achintya Kumar Sarkar, Srinivasan Umesh