Sciweavers

67 search results - page 6 / 14
» Multilingual acoustic modeling for speech recognition based ...
Sort
View
INTERSPEECH
2010
13 years 3 months ago
Discriminative adaptation for log-linear acoustic models
Log-linear models have recently been used in acoustic modeling for speech recognition systems. This has been motivated by competitive results compared to systems based on Gaussian...
Jonas Lööf, Ralf Schlüter, Hermann ...
CSL
2006
Springer
13 years 8 months ago
Product of Gaussians for speech recognition
Recently there has been interest in the use of classifiers based on the product of experts (PoE) framework. PoEs offer an alternative to the standard mixture of experts (MoE) fram...
M. J. F. Gales, S. S. Airey
TASLP
2010
117views more  TASLP 2010»
13 years 3 months ago
Speech Enhancement Using Gaussian Scale Mixture Models
This paper presents a novel probabilistic approach to speech enhancement. Instead of a deterministic logarithmic relationship, we assume a probabilistic relationship between the fr...
Jiucang Hao, Te-Won Lee, Terrence J. Sejnowski
ICML
2003
IEEE
14 years 9 months ago
Discriminative Gaussian Mixture Models: A Comparison with Kernel Classifiers
We show that a classifier based on Gaussian mixture models (GMM) can be trained discriminatively to improve accuracy. We describe a training procedure based on the extended Baum-W...
Aldebaro Klautau, Nikola Jevtic, Alon Orlitsky
ICASSP
2011
IEEE
13 years 8 days ago
HNM-based MFCC+F0 extractor applied to statistical speech synthesis
Currently, the statistical framework based on Hidden Markov Models (HMMs) plays a relevant role in speech synthesis, while voice conversion systems based on Gaussian Mixture Model...
Daniel Erro, Iñaki Sainz, Eva Navas, Inma H...