Knowledge representation is essential for semantics modeling and intelligent information processing. For decades researchers have proposed many knowledge representation techniques...
Abstract. This paper presents a brand-new Slovak text-to-speech system. It was developed within the framework of ARTIC system (primarily designed to synthesize Czech speech) with r...
We describe a framework for inducing probabilistic grammars from corpora of positive samples. First, samples are incorporated by adding ad-hoc rules to a working grammar; subseque...
Using discrete Hidden-Markov-Models (HMMs) for recognition requires the quantization of the continuous feature vectors. In handwritten whiteboard note recognition it turns out tha...
Corpus-based dialogue systems rely on statistical models, whose parameters are inferred from annotated dialogues. The dialogues are usually annotated using Dialogue Acts (DA), and...