Audio Visual Technique for Enhancing the Isolated Word Speech Recognition System

Main Article Content

N.S Sreekanth
N.K Narayanan

Abstract

This paper reports the enhancing of isolated word speech recognition system using audio visual features which are extracted from the context speech. Hand gestures captured which are co-expressive with speech are extracted from the context of speech. Both static and dynamic gestures are experimented as part of this study. The extracted gestural features are considered as augmenting features for improving the accuracy of isolated word speech recognition system. The performance of the system are measured under different noise conditions. The experimental results are tabulated under different signal to noise ratio conditions.

Keywords: Speech Recognition, Multimodal, Gesture recognition, Audio Visual Techniques, Non-acoustic features

Downloads

Download data is not yet available.

Article Details

Section
Articles