The speech parameter generation algorithm considering global variance (GV) for HMM-based speech synthesis proved to be effective against the over-smoothing problem. However, the c...
This paper presents techniques in clustering the sametopic news stories according to event themes. We model the relationship of stories with textual and visual concepts under the ...
Finding an accurate sparse approximation of a spectral vector described by a linear model, when there is available a library of possible constituent signals (called endmembers or ...
For the task of detecting shouted speech in a noisy environment, this paper introduces a system based on mel frequency cepstral coefficient (MFCC) feature extraction, unsupervise...
Visual action recognition is an important problem in computer vision. In this paper, we propose a new method to probabilistically model and recognize actions of articulated object...