Decoding Phone Pairs from MEG Signals Across Speech Modalities

TL;DR

This study demonstrates that MEG signals can decode phonetic information with high accuracy during speech production, highlighting the importance of neural oscillations in speech-related brain activity and informing brain-computer interface development.

Contribution

It introduces a comparative analysis of machine learning models for phoneme decoding from MEG signals during speech production and perception, emphasizing the significance of low-frequency oscillations.

Findings

Higher decoding accuracy during speech production (76.6%) than passive listening (~51%)

Elastic Net classifier outperformed neural networks in decoding tasks

Delta and Theta frequency bands significantly contributed to phoneme decoding

Abstract

Understanding the neural mechanisms underlying speech production is essential for both advancing cognitive neuroscience theory and developing practical communication technologies. In this study, we investigated magnetoencephalography signals to decode phones from brain activity during speech production and perception (passive listening and voice playback) tasks. Using a dataset comprising 17 participants, we performed pairwise phone classification, extending our analysis to 15 phonetic pairs. Multiple machine learning approaches, including regularized linear models and neural network architectures, were compared to determine their effectiveness in decoding phonetic information. Our results demonstrate significantly higher decoding accuracy during speech production (76.6%) compared to passive listening and playback modalities (~51%), emphasizing the richer neural information available during overt speech. Among the models, the Elastic Net classifier consistently outperformed more complex neural networks, highlighting the effectiveness of traditional regularization techniques when applied to limited and high-dimensional MEG datasets. Besides, analysis of specific brain frequency bands revealed that low-frequency oscillations, particularly Delta (0.2-3 Hz) and Theta (4-7 Hz), contributed the most substantially to decoding accuracy, suggesting that these bands encode critical speech production-related neural processes. Despite using advanced denoising methods, it remains unclear whether decoding solely reflects neural activity or if residual muscular or movement artifacts also contributed, indicating the need for further methodological refinement. Overall, our findings underline the critical importance of examining overt speech production paradigms, which, despite their complexity, offer opportunities to improve brain-computer interfaces to help individuals with severe speech impairments.