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...
Arnab Ghoshal, Daniel Povey, Mohit Agarwal, Pinar ...
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...
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...
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...
Discriminative mapping transforms (DMTs) is an approach to robustly adding discriminative training to unsupervised linear adaptation transforms. In unsupervised adaptation DMTs ar...