In this paper, we propose a general two-dimensional hidden Markov model (2D-HMM), where dependency of the state transition probability on any state is allowed as long as causality...
We present a three-step post-processing method for increasing the precision of video shot labels in the domain of television news. First, we demonstrate that news shot sequences c...
This paper introduces an novel framework for speech understanding using extended context-free grammars (ECFGs) by combining statistical methods and rule based knowledge. By only us...
In this paper, we propose a new stochastic language model that integrates local and global constraints effectively and describe a speechrecognition system basedon it. Theproposedl...
Abstract--This letter considers the average complexity of maximum-likelihood (ML) decoding of convolutional codes. ML decoding can be modeled as finding the most probable path take...