This paper applies time-varying autoregressive (TVAR) models with stochastically evolving parameters to the problem of speech modeling and enhancement. The stochastic evolution mod...
Large vocabulary continuous speech recognition (LVCSR) systems traditionally represent words in terms of smaller subword units. Both during training and during recognition, they re...
Abstract--This paper explores packet loss recovery for automatic speech recognition (ASR) in spoken dialog systems, assuming an architecture in which a lightweight client communica...
Constantinos Boulis, Mari Ostendorf, Eve A. Riskin...
-- We characterize the best achievable performance of lossy compression algorithms operating on arbitrary random sources, and with respect to general distortion measures. Direct an...
A new and efficient class of nonlinear receivers is introduced for digital communication systems. These "iterated-decision" receivers use optimized multipass algorithms t...