Children’s Emotion Recognition in an Intelligent Tutoring Scenario
Cached
Download Links
| Citations: | 6 - 1 self |
BibTeX
@MISC{Zhang_children’semotion,
author = {Tong Zhang and Mark Hasegawa-johnson and Stephen E. Levinson},
title = {Children’s Emotion Recognition in an Intelligent Tutoring Scenario},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
This paper presents an approach to automatically recognize emotion which children exhibit in an intelligent tutoring system. Emotion recognition can assist the computer agent to adapt its tutorial strategies to improve the efficiency of knowledge transmission. In this study, we detect three emotional classes: confidence, puzzle, and hesitation. Emotion is detected by means of lexical, prosodic, spectral, and syntactic analyses of users ’ speech. An automatic speech recognition system serves as the fundamental constituent of the system. A robust classification and regression tree (CART) integrates the various information sources together for final decision. The effectiveness of the proposed approach has been tested on data collected by Wizard-of-Oz (WoZ) experiments. Our emotion recognition was speaker-independent, and yielded 91.3 % accuracy. The test results showed that the spectral and duration-related prosodic features played very important roles in emotion recognition. 1.
Keyphrases
emotion recognition intelligent tutoring scenario automatic speech recognition system important role final decision syntactic analysis knowledge transmission emotional class robust classification various information source duration-related prosodic feature regression tree child exhibit tutorial strategy fundamental constituent test result computer agent
