Speech Recognition

In the GPM we are experts in audio and speech processing. Take a look into the projects section to see what we can do.

Computer Vision

As a research group we have developed projects in the fields of medical image, video surveillance, traffic analytics, tracking, object recognition, video coding, and much more.

video coding

We work to improve the next generation of video coding standards.

Welcome

The Group of Multimedia Processing (GPM) is part of the Department of Signal Theory and Communications, University Carlos III of Madrid.

Its research interests are in the general area of speech, audio, image and video processing, especially on computer vision, speech recognition, and last generation video coding. Besides applied research, the group also addresses more fundamental lines such as those devoted to audio-visual salience or emergent models of perception. Among the application sectors, the following deserve to be mentioned: medical image-based computer diagnosis systems, event and anomaly detection systems for security, and spoken man-machine interfaces for adverse conditions.