Master Thesis Presentation: Direct speech synthesis from EMG data

Student: Xabier Román

Advisor: Eva Navas

Presented: 05/10/21

Silent speech interfaces allow the generation of acoustic speech from articulatory data obtained from some sensors. In this master thesis we propose to develop a Neural Network based system able to produce speech from Electromiographic data. These data will come from a free available database (https://www.uni-bremen.de/en/csl/research/silent-speech-communication/).