We present an architecture for spoken dialogue systems where first-order inference (both theorem proving and model building) plays a crucial role in interpreting utterances of dia...
This paper proposes a learning and extracting method of word sequence correspondences from non-aligned parallel corpora with Support Vector Machines, which have high ability of th...
Human facial wrinkles can be eectively utilized for facial analysis. It is not an easy task, however, to extract features of wrinkledness directly from a camera image of a human f...
We argue that grammatical analysis is a viable alternative to concept spotting for processing spoken input in a practical spoken dialogue system. We discuss the structure of the g...
Gertjan van Noord, Gosse Bouma, Rob Koeling, Mark-...
In this paper we present an overview of the German version of the Bell Labs text-to-speech system, a high-quality concatenative synthesis system with extensive text analysis capab...