The Student’s-t hidden Markov model (SHMM) has been recently proposed as a robust to outliers form of conventional continuous density hidden Markov models, trained by means of t...
When no training or adaptation data is available, semisupervised training is a good alternative for processing new domains. We perform Bayesian training of a part-of-speech (POS) ...
Combilex is a high quality lexicon that has been developed specifically for speech technology purposes and recently released by CSTR. Combilex benefits from many advanced features...
We study the problem of image denoising where images are assumed to be samples from low dimensional (sub)manifolds. We propose the algorithm of locally linear denoising. The algor...
Alternating Gibbs sampling is the most common scheme used for sampling from Restricted Boltzmann Machines (RBM), a crucial component in deep architectures such as Deep Belief Netw...
Guillaume Desjardins, Aaron C. Courville, Yoshua B...