Automatic speech recognition system for Tamil language

Abstract

This paper presents a design and development of Speech Recognition System for Tamil languages. This system is based on CMU Sphinx 3 open sound speech recognition (ASR) engine developed by Carnegie Mellon University. This system should be adapt to speaker specific automatic, continues. One of the main components of this system is a core Tamil speech recognition system that can be trained with field specific data The target domain is the accent spoken by illiterate speaker in Tamil from Eastern area of Sri Lanka. The system is trained for speaker specific data and tested with speaker specific and speaker independent and has been adapted to home and office level back ground noise.