MKPLS: Manifold Kernel Partial Least Squares for Lipreading and Speaker Identification

Amr Bakry, Ahmed Elgammal; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013, pp. 684-691

Abstract


Visual speech recognition is a challenging problem, due to confusion between visual speech features. The speaker identification problem is usually coupled with speech recognition. Moreover, speaker identification is important to several applications, such as automatic access control, biometrics, authentication, and personal privacy issues. In this paper, we propose a novel approach for lipreading and speaker identification. We propose a new approach for manifold parameterization in a low-dimensional latent space, where each manifold is represented as a point in that space. We initially parameterize each instance manifold using a nonlinear mapping from a unified manifold representation. We then factorize the parameter space using Kernel Partial Least Squares (KPLS) to achieve a low-dimension manifold latent space. We use two-way projections to achieve two manifold latent spaces, one for the speech content and one for the speaker. We apply our approach on two public databases: AVLetters and OuluVS. We show the results for three different settings of lipreading: speaker independent, speaker dependent, and speaker semi-dependent. Our approach outperforms for the speaker semi-dependent setting by at least 15% of the baseline, and competes in the other two settings.

Related Material


[pdf]
[bibtex]
@InProceedings{Bakry_2013_CVPR,
author = {Bakry, Amr and Elgammal, Ahmed},
title = {MKPLS: Manifold Kernel Partial Least Squares for Lipreading and Speaker Identification},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2013}
}