Michael Ashby, Jill House, Mark Huckvale, John Maidment, Yanagisawa Ucl
Abstract This paper reports a project which aimed at making available most of the elements of traditional on-campus phonetic training within a Virtual Learning Environment (VLE). Benefits of the VLE...
Sarah Hawkins, Sebastian Heid, Jill House, Mark Huckvale
This paper describes the approach to the assessment of the naturalness of synthetic speech taken within the ProSynth collaborative speech synthesis project. The view expressed is that an important...
Evaluating Synthesised Prosody In Simulations Of An Automated Telephone Enquiry Service (2007)
Jill House, Catriona Macdermid, Scott Mcglashan, Andrew Simpson, Nick Youd
Dialogue material has been collected using bionic Wizard-of-Oz simulations of an automated voice-driven dialogue system; system turns, using rule-based speech synthesis, were systematically varied...
Sarah Hawkins, Jill House, Mark Huckvale, John Local, Richard Ogden
This paper outlines ProSynth, an approach to speech synthesis which takes a rich linguistic structure as central to the generation of natural-sounding speech. We start from the assumption that the...