Predicting Head Pose in Dyadic Conversation

Greenwood, David, Laycock, Stephen and Matthews, Iain (2017) Predicting Head Pose in Dyadic Conversation. In: International Conference on Intelligent Virtual Agents. Intelligent Virtual Agents, 10498 . Springer, pp. 160-169. ISBN 978-3-319-67400-1

Preview

PDF (Accepted manuscript) - Accepted Version Download (857kB) | Preview

Abstract

Natural movement plays a significant role in realistic speech animation. Numerous studies have demonstrated the contribution visual cues make to the degree we, as human observers, find an animation acceptable. Rigid head motion is one visual mode that universally co-occurs with speech, and so it is a reasonable strategy to seek features from the speech mode to predict the head pose. Several previous authors have shown that prediction is possible, but experiments are typically confined to rigidly produced dialogue. Expressive, emotive and prosodic speech exhibit motion patterns that are far more difficult to predict with considerable variation in expected head pose. People involved in dyadic conversation adapt speech and head motion in response to the others’ speech and head motion. Using Deep Bi-Directional Long Short Term Memory (BLSTM) neural networks, we demonstrate that it is possible to predict not just the head motion of the speaker, but also the head motion of the listener from the speech signal.

Item Type:	Book Section
Faculty \ School:	Faculty of Science > School of Computing Sciences
UEA Research Groups:	Faculty of Science > Research Groups > Interactive Graphics and Audio
Related URLs:	http://link.springer.com/10.1007/978-3-3...
Depositing User:	Pure Connector
Date Deposited:	13 Sep 2017 05:08
Last Modified:	01 Jun 2024 02:24
URI:	https://ueaeprints.uea.ac.uk/id/eprint/64845
DOI:	10.1007/978-3-319-67401-8_18

Downloads

Actions (login required)

View Item