A PCA based manifold representation for visual speech recognition

Abstract

In this paper, we discuss a new Principal Component Analysis (PCA)-based manifold representation for visual speech recognition. In this regard, the real time input video data is compressed using Principal Component Analysis and the low-dimensional points calculated for each frame define the manifold. Since the number of frames that form the video sequence is dependent on the word complexity, in order to use these manifolds for visual speech classification it is required to re-sample them into a fixed pre-defined number of key-points. These key-points are used as input for a Hidden Markov Model (HMM) classification scheme. We have applied the developed visual speech recognition system to a database containing a group of English words and the experimental data indicates that the proposed approach is able to produce accurate classification results.

Information Technology in an Improved Supervised Locally Linear Embedding for Recognizing Speech Emotion

“…In recent years, documents [2] have found out that feature data of speech signal is lying on a nonlinear manifold embedded in high-dimensional voice quality space. It made the manifold learning algorithms that aims at seeking inner structure information in high dimensional data can be used in nonlinear dimensionality reduction for speech feature data, such as lower dimensional speech for visualization [2] and speech recognition [3]. The main target of dimensionality is extracting the prime discriminated feature for low-dimensional embedding, discarding irrelevant or secondary important information and reducing the dimension of data.…”