Speech Synthesis Using EEG

In this paper we demonstrate speech synthesis using different electroencephalography (EEG) feature sets recently introduced in [1]. We make use of a recurrent neural network (RNN) regression model to predict acoustic features directly from EEG features. We demonstrate our results using EEG features...

Full description

Saved in:
Bibliographic Details
Published inProceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) pp. 1235 - 1238
Main Authors Krishna, Gautam, Tran, Co, Han, Yan, Carnahan, Mason, Tewfik, Ahmed H
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.05.2020
Subjects
Brain modeling
Deep Learning
EEG
Electroencephalography
Mel frequency cepstral coefficient
Predictive models
Recurrent neural networks
Speech synthesis
Training
Online AccessGet full text
ISSN2379-190X
DOI10.1109/ICASSP40776.2020.9053340

Cover

More Information
Summary:In this paper we demonstrate speech synthesis using different electroencephalography (EEG) feature sets recently introduced in [1]. We make use of a recurrent neural network (RNN) regression model to predict acoustic features directly from EEG features. We demonstrate our results using EEG features recorded in parallel with spoken speech as well as using EEG recorded in parallel with listening utterances. We provide EEG based speech synthesis results for four subjects in this paper and our results demonstrate the feasibility of synthesizing speech directly from EEG features.
ISSN:2379-190X
DOI:10.1109/ICASSP40776.2020.9053340