In this paper, we propose a new character generation method from on-line handwriting recognizers based on Bayesian networks. On-line handwriting recognizers are trained with handw...
We propose a new approach to estimate gait kinematics from image sequences taken by a monocular uncalibrated camera. This approach involves two generative models for gait represen...
Sign language is used for communicating to people with hearing difficulties. Recogntion of a sign language image sequence is challenging because of the variety of hand shapes and ...
In previous work [10], we considered algorithms related to the statistics of matches with words and regular expressions in texts generated by Bernoulli or Markov sources. In this w...
This paper presents a new approach to speech synthesis in which a set of cross-word decision-tree state-clustered context-dependent hidden Markov models are used to define a set o...