These pages are no longer up-to-date.
The activities are now carried on in the HLT research unit

CASPER

Comprehensive Automatic SPEech Recognition

introduction

CASPER - Comprehensive Automatic SPEech Recognition

The goal of this research line is to improve the technology involved in the extraction of linguistic information from audio data, coping with the issues that make automatic speech recognition in unconstrained domains still an open problem. Particular consideration is given to issues concerning robustness, genericity and efficiency of automatic transcription systems.


Updated: August 4, 2006
by myself