We investigate the performance of a machine-based lip-reading system using both shape-only parameters and full shape and appearance parameters. Furthermore, we contrast the performance of a machine-based lip-reading system with human lip-reading ability. We find that the automated system outperforms human lip-readers. Curiously however, for relatively simple tasks there is little improvement in recognition accuracy when adding full appearance features to the machine-based system, whereas for human lip-readers we observe significant improvements in performance. Finally, we measure the effect of ‘speaker training’ on human lip-reading ability and we find even very limited training is sufficient to improve performance.
|Number of pages
|Published - 2009
|AVSP 2009 - Norwich, United Kingdom
Duration: 10 Sep 2009 → 4 Oct 2009
|10/09/09 → 4/10/09