End-to-end speech synthesis from ECoG data recorded from epilepsy patients in the Universitätsklinikum Freiburg using Deep Neural Networks. The model architecture is based on recent speech recognition models such as the deepSpeech 2 model https://arxiv.org/abs/1512.02595.
arberzela / deepbrain Goto Github PK
View Code? Open in Web Editor NEWNeural Network for decoding ECoG brain signals into spoken language.
License: GNU General Public License v3.0