EMG-to-Speech with Fewer Channels

TL;DR

This study explores how reducing EMG channels affects speech reconstruction, demonstrating that pretraining and channel-aware strategies can maintain performance in lightweight silent speech interfaces.

Contribution

It introduces a pretraining and fine-tuning approach to mitigate performance loss from EMG channel reduction in silent speech systems.

Findings

Pretraining improves performance on reduced channels.

Certain channels are more informative for speech reconstruction.

Channel-aware design helps develop lightweight EMG-based speech interfaces.

Abstract

Surface electromyography (EMG) is a promising modality for silent speech interfaces, but its effectiveness depends heavily on sensor placement and channel availability. In this work, we investigate the contribution of individual and combined EMG channels to speech reconstruction performance. Our findings reveal that while certain EMG channels are individually more informative, the highest performance arises from subsets that leverage complementary relationships among channels. We also analyzed phoneme classification accuracy under channel ablations and observed interpretable patterns reflecting the anatomical roles of the underlying muscles. To address performance degradation from channel reduction, we pretrained models on full 8-channel data using random channel dropout and fine-tuned them on reduced-channel subsets. Fine-tuning consistently outperformed training from scratch for 4 - 6 channel settings, with the best dropout strategy depending on the number of channels. These results suggest that performance degradation from sensor reduction can be mitigated through pretraining and channel-aware design, supporting the development of lightweight and practical EMG-based silent speech systems.