This paper describes several new cepstral-based compensation procedures that render the SPHINX-II system more robust with respect to acoustical environment. The first algorithm, p...
Fu-Hua Liu, Pedro J. Moreno, Richard M. Stem, Alej...
We present an approach to music identification based on weighted finite-state transducers and Gaussian mixture models, inspired by techniques used in large-vocabulary speech recogn...
In this paper we propose an approach for action recognition based on a vocabulary of local motion-appearance features and fast approximate search in a large number of trees. Large...
In building a face recognition system for real-life scenarios, one usually faces the problem that is the selection of a feature-space and preprocessing methods such as alignment u...
A primary strength of the XCS approach is its ability to create maximally accurate general rules. In automatic target recognition (ATR) there is a need for robust performance beyo...