14 search results - page 1 / 3 » A novel estimation of feature-space MLLR for full-covariance... |
ICASSP
2010
IEEE
13 years 4 months ago
2010
IEEE
In this paper we present a novel approach for estimating featurespace maximum likelihood linear regression (fMLLR) transforms for full-covariance Gaussian models by directly maxim...
ICMCS
2005
IEEE
13 years 10 months ago
2005
IEEE
Multi-stream hidden Markov models (HMMs) have recently been very successful in audio-visual speech recognition, where the audio and visual streams are fused at the final decision...
ICASSP
2011
IEEE
12 years 8 months ago
2011
IEEE
In this paper, we propose a novel method for rapid feature space Maximum Likelihood Linear Regression (FMLLR) speaker adaptation based on bilinear models. When the amount of adapt...
ICASSP
2009
IEEE
13 years 2 months ago
2009
IEEE
In this paper, a novel method for speaker adaptation using bilinear model is proposed. Bilinear model can express both characteristics of speakers (style) and phonemes across spea...
ICASSP
2011
IEEE
12 years 8 months ago
2011
IEEE
Discriminative mapping transforms (DMTs) is an approach to robustly adding discriminative training to unsupervised linear adaptation transforms. In unsupervised adaptation DMTs ar...