SPEAKER - INDEPENDENT VISUAL LIP ACTIVITY DETECTION FOR HUMAN - COMPUTER INTERACTION

P.Sujatha, M.Radhakrishnan

Abstract: Recently there is an increased interest in using the visual features for improved speech processing. Lip reading plays a vital role in visual speech processing. In this paper, a new approach for lip reading is presented. Visual speech recognition is applied in mobile phone applications, human-computer interaction and also to recognize the spoken words of hearing impaired persons. The visual speech video is taken as input for face detection module which is used to detect the face region. The mouth region is identified based on the face region of interest (ROI). The mouth images are applied for feature extraction process. The features are extracted using every 10th coordinate, every 16th coordinate, 16 point + Discrete Cosine Transform (DCT) method and Lip DCT method. Then, these features are applied as inputs for recognizing the visual speech using Hidden Markov Model. Out of the different feature extraction methods, the DCT method gives the experimental results of better performance accuracy. 10 participants were uttered 35 different isolated words. For each word, 20 samples are collected for training and testing the process.

Keywords: Feature Extraction, HMM, Mouth ROI, DWT, Visual Speech Recognition

DOI: https://doi.org/10.15623/ijret.2013.0211084