Current video conference and phone systems do not provide the necessary tem
poral resolution and motion for speechreading. In this paper the perceptual
boundaries which effect speechreading performance are investigated. Analys
is of the relationships between viseme groupings, accuracy of viseme recogn
ition and presentation frame rate is presented based on the results of subj
ect testing. Results reveal a minimum frame rate of 10 frames per second (f
ps) for distinguishing viseme groupings. Confusion analysis results demonst
rate the importance of the tongue and teeth oral features for speechreading
. These results are critical to the design of speech-assisted video systems
to enhance speechreading for individuals with impaired hearing.