Audio Visual Isolated Oriya Digit Recognition Using HMM and DWT
Astik Biswas, Prasanna Kumar Sahu, Anirban Bhowmick, Mahesh Chandra · Proceedings of the Conference on Advances in Communication and Control Systems-2013 · 2013
Abstract. Automatic Speech Recognition (ASR) system performs well under restricted conditions but the performance degrades under noisy environment. Audio-visual features play an important role in ASR systems in presence of noise. In this paper Oriya isolated digit recognition system is designed using audio visual features. The visual features of the lip region integrated with audio features to get better recognition performance under noisy environments. Color Intensity and Pseudo Hue methods have been used for lip localization approach with Hidden Markov Model (HMM) as a classifier. For image compression principal component analysis technique has been utilized.