Development of speechreading supplements based on automatic speech recognition.

In manual-cued speech (MCS) a speaker produces hand gestures to resolve ambiguities among speech elements that are often confused by speechreaders. The shape of the hand distinguishes among consonants; the position of the hand relative to the face distinguishes among vowels. Experienced receivers of MCS achieve nearly perfect reception of everyday connected speech. MCS has been taught to very young deaf children and greatly facilitates language learning, communication, and general education. This manuscript describes a system that can produce a form of cued speech automatically in real time and reports on its evaluation by trained receivers of MCS. Cues are derived by a hidden markov models (HMM)-based speaker-dependent phonetic speech recognizer that uses context-dependent phone models and are presented visually by superimposing animated handshapes on the face of the talker. The benefit provided by these cues strongly depends on articulation of hand movements and on precise synchronization of the actions of the hands and the face. Using the system reported here, experienced cue receivers can recognize roughly two-thirds of the keywords in cued low-context sentences correctly, compared to roughly one-third by speechreading alone (SA). The practical significance of these improvements is to support fairly normal rates of reception of conversational speech, a task that is often difficult via SA.

Cephalometric comparisons of individuals from India and Mexico with unoperated cleft lip and palate.

The purpose of the study is to determine whether the presence of unoperated clefts of the lip and alveolus or cleft lip and palate have similar effects on the dentofacial relationships of individuals with different racial backgrounds. Nineteen individuals from India and eighteen from Mexico with either unoperated unilateral cleft lip and alveolus or unilateral cleft lip and palate were examined cephalometrically and compared to matched normal individuals. The first step in the data analysis was to compare the normal subjects in the Indian and Mexican samples. Because many statistically significant differences were found between the normal groups, each measure for each patient with a cleft was expressed as a percentage of the mean value for the matched normal group. These relative values for the different measures were then entered into analyses of variance to compare the Indian and Mexican groups with clefts. Subgroups with cleft lip and alveolus were analyzed separately from subgroups with cleft lip and palate. Few group comparisons based on the relative measures were statistically significant, thus suggesting that there was a great similarity in the dentofacial relationships of unoperated individuals with the same cleft type. If the present results are further substantiated by future studies, these findings should enable investigators to pool data on unoperated individuals from various sources. Such an approach can lead to a better understanding of the differences between the various cleft types while eliminating the masking effect of surgical or orthodontic treatment.