Inhomogeneous Gibbs model (IGM) [4] is an effective maximum entropy model in characterizing complex highdimensional distributions. However, its training process is so slow that th...
In this paper, we compare several approaches for the extraction of modulation frequency features from speech signal using a phoneme recognition system. The general framework in th...
Statistical models of word-sense disambiguation are often based on a small number of contextual features or on a model that is assumed to characterize the interactions among a set...
Previous work has shown that the difficulties in learning deep generative or discriminative models can be overcome by an initial unsupervised learning step that maps inputs to use...
Pascal Vincent, Hugo Larochelle, Yoshua Bengio, Pi...
In this work, we propose new graph-based data model and indexing to organize and manage video data. To consider spatial and temporal characteristics of video, we introduce a new g...