This paper presents a discriminative training (DT) approach to irrelevant variability normalization (IVN) based training of feature transforms and hidden Markov models for large v...
Developers of context-aware services, i.e. services that make use of sensory information from the environment of their users, often find testing and demonstrating services to be di...
This paper validates a recognition system using bidimensional wavelet transforms as feature extractor and investigates the relevance of each subband image in the recognition proce...
Segmenting the speech signals on the basis of time-frequency analysis is the most natural approach. Boundaries are located in places where energy of some frequency subband rapidly...
The paper addresses a problem of combining XML querying with ontology reasoning. We present an extension of a rule-based XML query and transformation language Xcerpt. The extensio...