# Towards Voice Reconstruction from EEG during Imagined Speech

arXiv: https://arxiv.org/abs/2301.07173 · HTML: https://mlsanity.com/paper/2301.07173/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jan 2023.

## Built on by (most cited first, 26 of 26)

- [BrainVis: Exploring the Bridge between Brain and Visual Signals via Image Reconstruction](https://mlsanity.com/paper/2312.14871/) (2023)
- [Diff-E: Diffusion-based Learning for Decoding Imagined Speech EEG](https://mlsanity.com/paper/2307.14389/) (2023)
- [Guess What I Think: Streamlined EEG-to-Image Generation with Latent Diffusion Models](https://mlsanity.com/paper/2410.02780/) (2024)
- [Toward Fully-End-to-End Listened Speech Decoding from EEG Signals](https://mlsanity.com/paper/2406.08644/) (2024)
- [Let EEG Models Learn EEG](https://mlsanity.com/paper/2605.21280/) (2026)
- [BELT:Bootstrapping Electroencephalography-to-Language Decoding and Zero-Shot Sentiment Classification by Natural Language Supervision](https://mlsanity.com/paper/2309.12056/) (2023)
- [Articulatory Feature Prediction from Surface EMG during Speech Production](https://mlsanity.com/paper/2505.13814/) (2025)
- [EEG2TEXT-CN: An Exploratory Study of Open-Vocabulary Chinese Text-EEG Alignment via Large Language Model and Contrastive Learning on ChineseEEG](https://mlsanity.com/paper/2506.00854/) (2025)
- [AI for Biomedicine in the Era of Large Language Models](https://mlsanity.com/paper/2403.15673/) (2024)
- [A Survey on Bridging EEG Signals and Generative AI: From Image and Text to Beyond](https://mlsanity.com/paper/2502.12048/) (2025)
- [Towards Dynamic Neural Communication and Speech Neuroprosthesis Based on Viseme Decoding](https://mlsanity.com/paper/2501.14790/) (2025)
- [An Approach to Simultaneous Acquisition of Real-Time MRI Video, EEG, and Surface EMG for Articulatory, Brain, and Muscle Activity During Speech Production](https://mlsanity.com/paper/2603.04840/) (2026)
- [NeuroSonic: Conditional Flow Matching for EEG-to-Speech Reconstruction](https://mlsanity.com/paper/2606.24087/) (2026)
- [Towards Unified Neural Decoding of Perceived, Spoken and Imagined Speech from EEG Signals](https://mlsanity.com/paper/2411.09243/) (2024)
- [S2M-Former: Spiking Symmetric Mixing Branchformer for Brain Auditory Attention Detection](https://mlsanity.com/paper/2508.05164/) (2025)
- [Neural Speech Embeddings for Speech Synthesis Based on Deep Generative Networks](https://mlsanity.com/paper/2312.05814/) (2023)
- [Dynamic Neural Communication: Convergence of Computer Vision and Brain-Computer Interface](https://mlsanity.com/paper/2411.09211/) (2024)
- [Imagined Speech State Classification for Robust Brain-Computer Interface](https://mlsanity.com/paper/2412.12215/) (2024)
- [A Silent Speech Decoding System from EEG and EMG with Heterogenous Electrode Configurations](https://mlsanity.com/paper/2506.13835/) (2025)
- [MiSTR: Multi-Modal iEEG-to-Speech Synthesis with Transformer-Based Prosody Prediction and Neural Phase Reconstruction](https://mlsanity.com/paper/2508.03166/) (2025)
- [Reconstructing Unseen Sentences from Speech-related Biosignals for Open-vocabulary Neural Communication](https://mlsanity.com/paper/2510.27247/) (2025)
- [EEG-to-Voice Decoding of Spoken and Imagined speech Using Non-Invasive EEG](https://mlsanity.com/paper/2512.22146/) (2025)
- [Brain-to-Speech: Prosody Feature Engineering and Transformer-Based Reconstruction](https://mlsanity.com/paper/2604.05751/) (2026)
- [MindVoice: Reconstructing Intelligible Speech from Non-invasive Neural Signals with Pretrained Priors](https://mlsanity.com/paper/2605.31173/) (2026)
- [Cross-Subject Semantic Decoding with Shared-Space Alignment for Generalized Neural Representation Learning](https://mlsanity.com/paper/2607.19394/) (2026)
- [Decoding Error-Related Potentials under Multisensory Feedback with Varying Congruency](https://mlsanity.com/paper/2607.24806/) (2026)

## Abstract (arXiv)

Translating imagined speech from human brain activity into voice is a challenging and absorbing research issue that can provide new means of human communication via brain signals. Endeavors toward reconstructing speech from brain activity have shown their potential using invasive measures of spoken speech data, however, have faced challenges in reconstructing imagined speech. In this paper, we propose NeuroTalk, which converts non-invasive brain signals of imagined speech into the user's own voice. Our model was trained with spoken speech EEG which was generalized to adapt to the domain of imagined speech, thus allowing natural correspondence between the imagined speech and the voice as a ground truth. In our framework, automatic speech recognition decoder contributed to decomposing the phonemes of generated speech, thereby displaying the potential of voice reconstruction from unseen words. Our results imply the potential of speech synthesis from human EEG signals, not only from spoken speech but also from the brain signals of imagined speech.