Automatic Analysis of Speech Prosody of Adolescents with Williams Syndrome and Their Typically Developing Peers

Presenter Information

Isaiah Houdek, Minnesota State University, Mankato
Tatyana Mamchuk, Minnesota State University, Mankato

Location

CSU Ballroom

Start Date

21-4-2008 1:00 PM

End Date

21-4-2008 3:00 PM

Student's Major

Electrical and Computer Engineering and Technology

Student's College

Science, Engineering and Technology

Mentor's Name

Rebecca Bates

Mentor's Department

Computer Information Science

Mentor's College

Science, Engineering and Technology

Second Mentor's Name

Patricia Hargrove

Second Mentor's Department

Speech, Hearing, and Rehabilitation Services

Second Mentor's College

Allied Health and Nursing

Description

People with the genetic disorder Williams Syndrome often display differences in their speech and language abilities that do not directly correlate with their IQs. Using data acquired and transcribed by the Communications Disorders Program, this work compares patterns of prosody (in part, stress and intonation) in the speech of adolescents with Williams Syndrome and their typically developing peers. The data has been prepared by digitizing the speech waveforms and segmenting the speech into utterances. Using acoustic measurements of pitch, energy, and duration, we performed a statistical analysis of speech that includes factors such as age and gender.