Two different systems are proposed for the task of capitalisation generation. The first system is a slightly modified speech recogniser. In this system, every word in the vocabula...
This paper explores the problem of identifying sentence boundaries in the transcriptions produced by automatic speech recognition systems. An experiment which determines the level...
We describe a system for automatically extracting dynamics of tongue gestures from ultrasound images of the tongue using translational deep belief networks (tDBNs). In tDBNs, a jo...
The Text2Dialogue (T2D) system that we are developing allows digital content creators to generate attractive multi-modal dialogues presented by two virtual agents—by simply provi...
Paul Piwek, Hugo Hernault, Helmut Prendinger, Mits...
An algorithm is proposed which automatically estimates the local signalto-noise ratio (SNR) between speech and noise. The feature extraction stage of the algorithm is motivated by...