Figure 8 - uploaded by Li Liu
Content may be subject to copyright.
Download
View publication
12: Confusion matrices for three single stream viseme recognition. (a), (b) and (c) are recognitions based on 8 hand shapes, 8 lips visemes and 5 hand positions. The class "silence" (the first element) is included in the confusion matrix. The red rectangle contains the concerning visemes. The last column corresponds to the deletion error D, and the last row corresponds to the insertion error I. The brighter element corresponds to the higher occurrence in these confusion matrices.

12: Confusion matrices for three single stream viseme recognition. (a), (b) and (c) are recognitions based on 8 hand shapes, 8 lips visemes and 5 hand positions. The class "silence" (the first element) is included in the confusion matrix. The red rectangle contains the concerning visemes. The last column corresponds to the deletion error D, and the last row corresponds to the insertion error I. The brighter element corresponds to the higher occurrence in these confusion matrices.

Source publication
Figure 1: Framework of the automatic CS recognition from visual...
Figure 1.1: Examples of cueing American English CS (from the NCSA).
Figure 1.2: Manual cues of American English CS (from [31]).
Figure 1.3: Manual cues of LPC (from [10]).
+116 Figure 1.4: One example of SL, signing "hello" 6 .
LiLIU thesis archivage
Thesis
Full-text available
  • Sep 2018
This PhD thesis deals with the automatic continuous Cued Speech (CS) recognition in French based on the images of subjects without using any artificial landmark. In order to realize this objective, we extract high-level features of three information flows (lips, hand positions and shapes), and find an optimal approach to merge them for a robust CS...
Cite
Download full-text