Using group history to identify character-directed utterances in multi-child interactions - Robotics Institute Carnegie Mellon University

Using group history to identify character-directed utterances in multi-child interactions

Hannaneh Hajishirzi, Jill F. Lehman, and Jessica K. Hodgins
Conference Paper, Proceedings of 13th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL '12), pp. 207 - 216, July, 2012

Abstract

Addressee identification is an element of all language-based interactions, and is critical for turn-taking. We examine the particular problem of identifying when each child playing an interactive game in a small group is speaking to an animated character. After analyzing child and adult behavior, we explore a family of machine learning models to integrate audio and visual features with temporal group interactions and limited, task-independent language. The best model performs identification about 20% better than the model that uses the audio-visual features of the child alone.

BibTeX

@conference{Hajishirzi-2012-121995,
author = {Hannaneh Hajishirzi and Jill F. Lehman and Jessica K. Hodgins},
title = {Using group history to identify character-directed utterances in multi-child interactions},
booktitle = {Proceedings of 13th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL '12)},
year = {2012},
month = {July},
pages = {207 - 216},
}