# Physiological Noise Augmentation Improves Non-Invasive Brain-to-Speech

arXiv: https://arxiv.org/abs/2607.05165 · HTML: https://mlsanity.com/paper/2607.05165/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 65 references that are in the map.
- First posted on arXiv 6 Jul 2026.

## Builds on (most cited first, 24 of 24)

- [Model evaluation for extreme risks](https://mlsanity.com/paper/2305.15324/) (2023)
- [Frontier AI Regulation: Managing Emerging Risks to Public Safety](https://mlsanity.com/paper/2307.03718/) (2023)
- [Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database](https://mlsanity.com/paper/2011.08512/) (2020)
- [Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents](https://mlsanity.com/paper/2509.26354/) (2025)
- [From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM Agents](https://mlsanity.com/paper/2606.04990/) (2026)
- [A Framework of Severity for Harmful Content Online](https://mlsanity.com/paper/2108.04401/) (2021)
- [Towards Trustworthy AI: A Review of Ethical and Robust Large Language Models](https://mlsanity.com/paper/2407.13934/) (2024)
- [Async Control: Stress-testing Asynchronous Control Measures for LLM Agents](https://mlsanity.com/paper/2512.13526/) (2025)
- [Safety cases for frontier AI](https://mlsanity.com/paper/2410.21572/) (2024)
- [The AI risk repository: A meta-review, database, and taxonomy of risks from artificial intelligence](https://mlsanity.com/paper/2408.12622/) (2024)
- [A False Sense of Privacy: Evaluating Textual Data Sanitization Beyond Surface-level Privacy Leakage](https://mlsanity.com/paper/2504.21035/) (2025)
- [A taxonomic system for failure cause analysis of open source AI incidents](https://mlsanity.com/paper/2211.07280/) (2022)
- [Deployment Corrections: An incident response framework for frontier AI models](https://mlsanity.com/paper/2310.00328/) (2023)
- [Trustworthy AI: Securing Sensitive Data in Large Language Models](https://mlsanity.com/paper/2409.18222/) (2024)
- [The Role of Governments in Increasing Interconnected Post-Deployment Monitoring of AI](https://mlsanity.com/paper/2410.04931/) (2024)
- [Exploring the Relevance of Data Privacy-Enhancing Technologies for AI Governance Use Cases](https://mlsanity.com/paper/2303.08956/) (2023)
- [Designing Incident Reporting Systems for Harms from General-Purpose AI](https://mlsanity.com/paper/2511.05914/) (2025)
- [Standardised schema and taxonomy for AI incident databases in critical digital infrastructure](https://mlsanity.com/paper/2501.17037/) (2025)
- [From Incidents to Insights: Patterns of Responsibility following AI Harms](https://mlsanity.com/paper/2505.04291/) (2025)
- [Incident Analysis for AI Agents](https://mlsanity.com/paper/2508.14231/) (2025)
- [Slice it up: Unmasking User Identities in Smartwatch Health Data](https://mlsanity.com/paper/2308.08310/) (2023)
- [An Empirical Study of Production Incidents in Generative AI Cloud Services](https://mlsanity.com/paper/2504.08865/) (2025)
- [The AI Model Risk Catalog: What Developers and Researchers Miss About Real-World AI Harms](https://mlsanity.com/paper/2508.16672/) (2025)
- [AI Harmonics: a human-centric and harms severity-adaptive AI risk assessment framework](https://mlsanity.com/paper/2509.10104/) (2025)

## Abstract (arXiv)

Non-invasive brain-to-speech decoding aims to restore communication to patients suffering from neurodegenerative disease, without the risks of neurosurgery. Existing MEG- and EEG-based methods, while scalable, continue to suffer from high word error rates driven by relatively low signal-to-noise ratios compared to invasive recordings. We propose physiological noise augmentation (PNA), a data augmentation method that explicitly trains decoders to become invariant to task-agnostic artifacts (e.g. ocular and cardiac activity). PNA draws inspiration from automatic speech recognition systems, where environmental noise (e.g. dogs barking, city traffic) is added to clean speech to improve robustness. Analogously, we decompose brain recordings into clean data and noise artifacts using independent component analysis (ICA), before scaling and remixing to generate biophysically realistic, label-preserving training examples. We show that PNA approximates anisotropic regularization, penalizing decoder sensitivity along artifact-dominated directions. On MegNIST, a 12k-trial imagined-digit MEG dataset, PNA with 10-trial averaging improves EEGNet decoding accuracy by 4.7 percentage points (absolute) over training on real data alone. Our results suggest that artifact-aware augmentation and trial averaging are complementary tools for improving robustness in non-invasive speech BCIs.