When exposed to environmental noise, speakers adjust their speech production to maintain intelligible communication. This phenomenon, called Lombard effect (LE), is known to consi...
We propose a model for speech recognition that consists of multiple semi-synchronized recognizers operating on a polyphase decomposition of standard speech features. Specifically...
A novel region-based multiple object tracking framework based on Kalman filtering and elastic matching is proposed. The proposed Kalman filtering-elastic matching model is gener...
automatically updated during the matching process, This paper describes a real-time tracking system which detects an object entering into the field of view of camera and executes t...
Image-based modeling of semi-transparent, dynamic phenomena is a challenging task. We present an optical tomography method that uses an adaptive grid for the reconstruction of a t...