# NeuroSonic: Conditional Flow Matching for EEG-to-Speech Reconstruction

arXiv: https://arxiv.org/abs/2606.24087 · HTML: https://mlsanity.com/paper/2606.24087/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 20 of its 31 references that are in the map.
- First posted on arXiv 23 Jun 2026.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 20 of 20)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Mean Flows for One-step Generative Modeling](https://mlsanity.com/paper/2505.13447/) (2025)
- [DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors](https://mlsanity.com/paper/2010.15258/) (2020)
- [Mousai: Text-to-Music Generation with Long-Context Latent Diffusion](https://mlsanity.com/paper/2301.11757/) (2023)
- [EEGFormer: Towards Transferable and Interpretable Large-Scale EEG Foundation Model](https://mlsanity.com/paper/2401.10278/) (2024)
- [MedGen3D: A Deep Generative Framework for Paired 3D Image and Mask Generation](https://mlsanity.com/paper/2304.04106/) (2023)
- [Calibrating Multi-modal Representations: A Pursuit of Group Robustness without Annotations](https://mlsanity.com/paper/2403.07241/) (2024)
- [Self-supervised Dialogue Learning for Spoken Conversational Question Answering](https://mlsanity.com/paper/2106.02182/) (2021)
- [Towards Voice Reconstruction from EEG during Imagined Speech](https://mlsanity.com/paper/2301.07173/) (2023)
- [Adaptive Bi-directional Attention: Exploring Multi-Granularity Representations for Machine Reading Comprehension](https://mlsanity.com/paper/2012.10877/) (2020)
- [Uncovering Memorization Effect in the Presence of Spurious Correlations](https://mlsanity.com/paper/2501.00961/) (2025)
- [Ouroboros: Single-step Diffusion Models for Cycle-consistent Forward and Inverse Rendering](https://mlsanity.com/paper/2508.14461/) (2025)
- [Aligning Source Visual and Target Language Domains for Unpaired Video Captioning](https://mlsanity.com/paper/2211.12148/) (2022)
- [Stable Velocity: A Variance Perspective on Flow Matching](https://mlsanity.com/paper/2602.05435/) (2026)
- [CineBrain: A Large-Scale Multi-Modal Brain Dataset During Naturalistic Audiovisual Narrative Processing](https://mlsanity.com/paper/2503.06940/) (2025)
- [Let EEG Models Learn EEG](https://mlsanity.com/paper/2605.21280/) (2026)
- [Scale Where It Matters: Training-Free Localized Scaling for Diffusion Models](https://mlsanity.com/paper/2511.19917/) (2025)
- [Inter- and Intra-Subject Variability in EEG: A Systematic Survey](https://mlsanity.com/paper/2602.01019/) (2026)

## Built on by (most cited first, 2 of 2)

- [Brain-to-Language Decoding: Tasks, Signals, Methods, Evaluation, Practical Use and Beyond](https://mlsanity.com/paper/2609.27650/) (2026)
- [Test-Time Registers as Global Priors for Tokenized Image Generation](https://mlsanity.com/paper/2607.16824/) (2026)

## Abstract (arXiv)

Reconstructing continuous speech from scalp electroencephalography (EEG) remains fundamentally challenging. EEG provides a weak, spatially diffuse, and highly variable measurement of distributed cortical activity, whereas speech is organized as a coherent acoustic trajectory with strong harmonic and temporal structure. The resulting mismatch makes waveform regression unstable and causes stochastic multi-step generation to be sensitive to artifact-dependent conditioning and subject variability. We introduce NeuroSonic, a conditional flow-matching framework for EEG-to-speech reconstruction. Instead of predicting waveforms directly or refining them through stochastic denoising, NeuroSonic learns a deterministic probability-flow velocity field that transports a noise-corrupted acoustic state toward clean speech under EEG conditioning. EEG and audio are embedded into a shared token space and processed by a time-conditioned gated Transformer that parameterizes the transport ordinary differential equation. This formulation models trajectory evolution explicitly while avoiding iterative stochastic sampling. We evaluate NeuroSonic on the CineBrain and EAV benchmarks under cross-subject evaluation. Across both datasets, the proposed method improves distributional realism, spectral fidelity, and perceptual quality over representative GAN-, diffusion-, and mean-flow baselines, with up to a 26.3% gain in overall perceptual quality. The performance gap is most evident in artifact-heavy segments, where conditioning variability is strongest. These findings indicate that deterministic conditional transport provides a stable and effective formulation for EEG-driven speech reconstruction. Code is available at https://github.com/Y-Research-SBU/NeuroSonic/ .