The ASKNet project uses a combination of NLP tools and spreading activation to transform natural language text into semantic knowledge networks. Network fragments are generated fr...
We study local interchangeability of values in constraint networks based on a new approach where a single value in the domain of a variable can be treated as a combination of &quo...
This paper introduces a new registration method estimating the displacement field of bodies which deformations are constrained by an articulated rigid body. We propose an articula...
Aloys du Bois d'Aische, Mathieu De Craene, Beno&ic...
Model compensation is a standard way of improving the robustness of speech recognition systems to noise. A number of popular schemes are based on vector Taylor series (vts) compen...
Multi-stream hidden Markov models (HMMs) have recently been very successful in audio-visual speech recognition, where the audio and visual streams are fused at the final decision...