Data
indicating the effectiveness of state-of-art facial animation for speech
training compared to natural faces
Figure
1: Difference in correct identification of /l/-/r/ consonant pre-post training
in the three test condition for the two learner groups who undertook training
with either auditory or audiovisual stimuli.
19 listeners
were trained with audiovisual training provided by a conversational agent so
that a comparison could be made with the 25 students trained with a natural
face (see details here). Comparing those two
groups only, we found that listeners trained with a natural face improved their
perception more than those trained with an artificial face.