Litcius/Paper detail

Speech Synthesis Using EEG

Gautam Krishna, Co Tran, Yan Han, Mason Carnahan, Ahmed H Tewfik

202010 citationsDOIOpen Access PDF

Abstract

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.

Topics & Concepts

ElectroencephalographySpeech recognitionComputer scienceFeature (linguistics)Active listeningArtificial neural networkArtificial intelligencePattern recognition (psychology)PsychologyCommunicationLinguisticsNeurosciencePhilosophySpeech Recognition and SynthesisEEG and Brain-Computer InterfacesSpeech and Audio Processing
Speech Synthesis Using EEG | Litcius