A Cross-Modal Approach to Silent Speech with LLM-Enhanced Recognition

TL;DR

This paper presents MONA, a cross-modal silent speech recognition system enhanced by LLM scoring, achieving significant reductions in word error rate and demonstrating the viability of noninvasive silent speech interfaces as alternatives to traditional ASR.

Contribution

Introduces MONA with novel loss functions and LISA, enabling silent speech recognition on open vocabulary with state-of-the-art accuracy improvements.

Findings

Reduced silent speech WER from 28.8% to 12.2% on benchmark datasets.

Achieved 3.7% WER on vocal EMG recordings, surpassing previous state-of-the-art.

Performed best in Brain-to-Text 2024 competition, with top WER of 8.9%.

Abstract

Silent Speech Interfaces (SSIs) offer a noninvasive alternative to brain-computer interfaces for soundless verbal communication. We introduce Multimodal Orofacial Neural Audio (MONA), a system that leverages cross-modal alignment through novel loss functions--cross-contrast (crossCon) and supervised temporal contrast (supTcon)--to train a multimodal model with a shared latent representation. This architecture enables the use of audio-only datasets like LibriSpeech to improve silent speech recognition. Additionally, our introduction of Large Language Model (LLM) Integrated Scoring Adjustment (LISA) significantly improves recognition accuracy. Together, MONA LISA reduces the state-of-the-art word error rate (WER) from 28.8% to 12.2% in the Gaddy (2020) benchmark dataset for silent speech on an open vocabulary. For vocal EMG recordings, our method improves the state-of-the-art from 23.3% to 3.7% WER. In the Brain-to-Text 2024 competition, LISA performs best, improving the top WER from 9.8% to 8.9%. To the best of our knowledge, this work represents the first instance where noninvasive silent speech recognition on an open vocabulary has cleared the threshold of 15% WER, demonstrating that SSIs can be a viable alternative to automatic speech recognition (ASR). Our work not only narrows the performance gap between silent and vocalized speech but also opens new possibilities in human-computer interaction, demonstrating the potential of cross-modal approaches in noisy and data-limited regimes.