In this work we present two extensions to the well-known dynamic programming beam search in phrase-based statistical machine translation (SMT), aiming at increased efficiency of ...
In this paper, a new learning framework?probabilistic boosting-tree (PBT), is proposed for learning two-class and multi-class discriminative models. In the learning stage, the pro...
— Traditional approaches to integrating knowledge into neural network are concerned mainly about supervised learning. This paper presents how a family of self-organizing neural m...
We consider the problem of obtaining the approximate maximum a posteriori estimate of a discrete random field characterized by pairwise potentials that form a truncated convex mod...
It is well known that the classical linear predictive model for speech fails to take into account the quasi-periodic nature of the glottal flow typical of voiced speech. In this ...