Select Publications

2021

Importance of Parasagittal Sensor Information in Tongue Motion Capture through a Diphonic Analysis
Sarah Taylor, Salvador Medina∗, Mark Tiede, Alexander Hauptmann and Iain Matthews
Interspeech, September 2021
[Paper]
(Equal contribution)

Speaker-independent Speech Animation using Perceptual Loss Functions and Synthetic Data
Danny Websdale, Sarah Taylor and Ben Milner
IEEE Transactions on Multimedia
[Early Access Paper]

2019

*BEST SHORT PAPER AWARD*
Joint Estimation of Face and Camera Pose (Short paper and poster)
David Greenwood, Sarah Taylor and Iain Matthews
CVMP, December 2019
[Project page]

Synthesising Visual Speech using Dynamic Visemes and Deep Learning Architectures
Ausdang Thangthai, Ben Milner, Sarah Taylor
Computer Speech & Language, May 2019
[Paper]

2018

Joint Learning of Facial Expression and Head Pose from Speech
David Greenwood, Iain Matthews, and Stephen Laycock
Interspeech, September 2018
[Paper]

The Effect of Real-Time Constraints on Automatic Speech Animation
Danny Websdale, Sarah Taylor, Ben Milner
Interspeech, September 2018
[Paper]

2017

A Deep Learning Approach for Generalized Speech Animation
Sarah L. Taylor, Taehwan Kim, Yisong Yue, Moshe Mahler, James Krahe, Anastasio Garcia Rodriguez, Jessica Hodgins, and Iain Matthews
ACM Transactions on Graphics (Proc. ACM SIGGRAPH), August 2017
[Paper] [Supplementary Movie]

Predicting Head Pose in Dyadic Conversation
David Greenwood, Stephen Laycock, and Iain Matthews
Intelligent Virtual Agents, August 2017
[Paper]

Predicting Head Pose from Speech with a Conditional Variational Autoencoder
David Greenwood, Stephen Laycock, and Iain Matthews
Interspeech, August 2017
[Paper]

2016

Audio-to-Visual Speech Conversion Using Deep Neural Networks
S Taylor, A Kato, I Matthews, B Milner
Interspeech, September 2016
[Paper]