We describe an acoustic modeling approach in which all phonetic states share a common Gaussian Mixture Model structure, and the means and mixture weights vary in a subspace of the...
Daniel Povey, Lukas Burget, Mohit Agarwal, Pinar A...
Although research has previously been done on multilingual speech recognition, it has been found to be very difficult to improve over separately trained systems. The usual approa...
Lukas Burget, Petr Schwarz, Mohit Agarwal, Pinar A...
This paper 1 proposes a technique for simplifying a given Gaussian mixture model, i.e. reformulating the density in a more parcimonious manner, if possible (less Gaussian componen...
In this paper, a spatially constrained mixture model for the segmentation of MR brain images is presented. The novelty of this work is a new, edge preserving, smoothness prior whic...
Giorgos Sfikas, Christophoros Nikou, Nikolas P. ...
Current approaches to pose estimation and tracking can be classified into two categories: generative and discriminative. While generative approaches can accurately determine human...
Abhinav Gupta, Trista Chen, Francine Chen, Don Kim...