Predicting Different Acoustic Features from EEG and towards direct synthesis of Audio Waveform from EEG

2020-05-29 · Gautam Krishna, Co Tran, Mason Carnahan, Ahmed Tewfik

In [1,2] authors provided preliminary results for synthesizing speech from electroencephalography (EEG) features where they first predict acoustic features from EEG features and then the speech is reconstructed from the predicted acoustic features using griffin lim reconstruction algorithm. In this paper we first introduce a deep learning model that takes raw EEG waveform signals as input and directly produces audio waveform as output. We then demonstrate predicting 16 different acoustic features from EEG features. We demonstrate our results for both spoken and listen condition in this paper. The results presented in this paper shows how different acoustic features are related to non-invasive neural EEG signals recorded during speech perception and production.

📄 PDF Abstract BibTeX arXiv:2006.01262

Code (0)

등록된 구현이 없습니다.

Tasks

EEGElectroencephalogram (EEG)

Advancing Speech Synthesis using EEG

2020-04-09 · Gautam Krishna, Co Tran, Mason Carnahan, Ahmed Tewfik

In this paper we introduce attention-regression model to demonstrate predicting acoustic features from electroencephalography (EEG) features recorded in parallel with spoken sentences. First we demonstrate predicting aco…

EEG Electroencephalogram (EEG)regression Speech Synthesis

Generating EEG features from Acoustic features

2020-02-29 · Gautam Krishna, Co Tran, Mason Carnahan, Yan Han 외

In this paper we demonstrate predicting electroencephalograpgy (EEG) features from acoustic features using recurrent neural network (RNN) based regression model and generative adversarial network (GAN). We predict variou…

EEG Electroencephalogram (EEG)Generative Adversarial Network regression+1

Speech Synthesis using EEG

2020-02-22 · Gautam Krishna, Co Tran, Yan Han, Mason Carnahan

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 fea…

EEG Electroencephalogram (EEG)regression Speech Synthesis

Vector-Quantized Timbre Representation

2020-07-13 · Adrien Bitton, Philippe Esling, Tatsuya Harada

Timbre is a set of perceptual attributes that identifies different types of sound sources. Although its definition is usually elusive, it can be seen from a signal processing viewpoint as all the spectral features that a…

Which Prosodic Features Matter Most for Pragmatics?

2024-08-23 · Nigel G. Ward, Divette Marco, Olac Fuentes

We investigate which prosodic features matter most in conveying prosodic functions. We use the problem of predicting human perceptions of pragmatic similarity among utterance pairs to evaluate the utility of prosodic fea…

Speech Synthesis