Speech Synthesis Using EEG

Speech Synthesis Using EEG
复制标题

DOI:
10.1109/icassp40776.2020.9053340
复制
发表时间:
2020-02
期刊:
ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
影响因子:
--
通讯作者:
G. Krishna;Co Tran;Yan Han;Mason Carnahan
G. Krishna;Co Tran;Yan Han;Mason Carnahan
中科院分区:
其他
文献类型:
--
作者:
G. Krishna;Co Tran;Yan Han;Mason Carnahan

文献摘要

被引文献

相似文献

在本文中,我们演示了语音合成使用不同的脑电图(EEG)功能集最近在[1]中介绍。我们利用一个递归神经网络(RNN)回归模型来预测直接从EEG特征的声学特征。我们使用与口语并行记录的EEG特征以及与听力话语并行记录的EEG来展示我们的结果。本文提供了四个受试者的基于脑电的语音合成结果,我们的结果证明了直接从脑电特征合成语音的可行性。
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.