Sarah A. Cassidy, B. Stenger, L. Dongen, K. Yanagisawa, Robert Anderson, V. Wan, S. Baron-Cohen, R. Cipolla
tlooto Summary
A videorealistic avatar, XpressiveTalk, which speaks in various emotional tones is shown and emotion-recognition and preference studies are carried out, finding that adults with ASC are less accurate than controls, but above chance levels for inferring emotions.
Abstract
Highlights • We show a videorealistic avatar, XpressiveTalk, which speaks in various emotional tones.• The use as an assistive technology for people with autism spectrum conditions (ASC) is discussed.• We carry out emotion-recognition and preference studies.• Adults with ASC are less accurate than controls, but above chance levels for inferring emotions.
Citation format
CASSIDY, Sarah A., et al. Expressive visual text-to-speech as an assistive technology for individuals with autism spectrum conditions. COMPUTER VISION AND IMAGE UNDERSTANDING, 2016, 148: 193–200.