# Speech Synthesis using EEG

arXiv: https://arxiv.org/abs/2002.12756 · HTML: https://mlsanity.com/paper/2002.12756/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Feb 2020.

## Built on by (most cited first, 8 of 8)

- [Decoding speech perception from non-invasive brain recordings](https://mlsanity.com/paper/2208.12266/) (2022)
- ["Hello, It's Me": Deep Learning-based Speech Synthesis Attacks in the Real World](https://mlsanity.com/paper/2109.09598/) (2021)
- [CineBrain: A Large-Scale Multi-Modal Brain Dataset During Naturalistic Audiovisual Narrative Processing](https://mlsanity.com/paper/2503.06940/) (2025)
- [End-to-end translation of human neural activity to speech with a dual-dual generative adversarial network](https://mlsanity.com/paper/2110.06634/) (2021)
- [BASEN: Time-Domain Brain-Assisted Speech Enhancement Network with Convolutional Cross Attention in Multi-talker Conditions](https://mlsanity.com/paper/2305.09994/) (2023)
- [Towards a practical lip-to-speech conversion system using deep neural networks and mobile application frontend](https://mlsanity.com/paper/2104.14467/) (2021)
- [Decoding Linguistic Representations of Human Brain](https://mlsanity.com/paper/2407.20622/) (2024)
- [Brain Signals to Rescue Aphasia, Apraxia and Dysarthria Speech Recognition](https://mlsanity.com/paper/2103.00383/) (2021)

## Abstract (arXiv)

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.