Lead Institution: University of Sheffield Dr Jose A. Gonzalez
University of Leeds: Dr Andy Bulpitt
University of York: Dr Damian Murphy
Every year, some 17500 people in Europe and North America lose the power of speech after undergoing a laryngectomy. In Sheffield, we have recently demonstrated that it is possible to restore speech to these people by a learned transformation from articulator movement to sound . Articulator movement is captured by a technique developed by our collaborators at Hull University called PMA (Permanent Magnet Articulography), which senses the changes of magnetic field caused by movements of small magnets attached to the lips and tongue. This solution, however, requires synchronous PMA-and-audio recordings for learning the transformation and, hence, it cannot be applied to people who have already lost their voice. Here we propose to investigate a variant of this technique in which the PMA data are used to drive an articulatory synthesiser, which synthesises speech by simulating the airflow through a computational model of the vocal tract. Our objectives are therefore
1. To train a direct transformation from PMA data to vocal tract shapes used by the articulatory synthesiser.
2. To personalise the synthesiser so that the speech generated sounds like the user’s original voice, using MRI vocal tract imaging.
Other staff involved with this project
Leeds: Dr Duane Carey
Sheffield: Prof Phil D. Green and Prof Roger K. Moore
York: Dr Helena Daffern and Ms Amelia Gully
University of Hull: Prof James M. Gilbert and Dr Lam A. Cheah