In this paper, we introduce a novel bayesian compressive sensing (CS) technique for phonetic classification. CS is often used to characterize a signal from a few support training...
Tara N. Sainath, Avishy Carmi, Dimitri Kanevsky, B...
We describe feature space and model space discriminative training for a new class of acoustic models called Bayesian sensing hidden Markov models (BS-HMMs). In BS-HMMs, speech dat...
We present a method for unsupervised learning of classes of motions in video. We project optical flow fields to a complete, orthogonal, a-priori set of basis functions in a probab...
Abstract. An effective way to examine causality is to conduct an experiment with random assignment. However, in many cases it is impossible or too expensive to perform controlled ...
This paper presents a novel Gaussianized vector representation for scene images by an unsupervised approach. First, each image is encoded as an ensemble of orderless bag of featur...
Hao Tang, Mark Hasegawa-Johnson, Thomas S. Huang, ...