Speech recognition is a computationally demanding task, particularly the stage which uses Viterbi decoding for converting pre-processed speech data into words or sub-word units. W...
Stephen J. Melnikoff, Steven F. Quigley, Martin J....
In previous work [14], we modify the hidden Markov model (HMM) framework to incorporate a global parametric variation in the output probabilities of the states of the HMM. Develop...
Up-propagation is an algorithm for inverting and learning neural network generative models. Sensory input is processed by inverting a model that generates patterns from hidden var...
Occlusion is a difficult problem for appearance-based target tracking, especially when we need to track multiple targets simultaneously and maintain the target identities during t...
We develop a novel extension to the Ratio Semi-definite Classifier, a discriminative model formulated as a ratio of semi-definite polynomials. By adding a hidden layer to the m...