# PhonoBridge preprint reports lower error rate in silent-speech decoding

_Published Wednesday, October 21, 2026 at 1:05 AM EDT · Science, AI · Latest · Tier 2 — Notable_

Researchers report that PhonoBridge, a system for converting silently articulated speech into text using muscle signals, achieved a 24.77% word error rate on the Open Vocabulary silent-speech dataset. The preprint compares that result with the previously reported best of 28.27% on the same test split.

The system first converts electromyography signals into phonemes, then uses a large language model to reconstruct text. It expands training data using phoneme-text pairs derived from LibriSpeech transcripts without additional muscle recordings, introducing errors that mimic the frontend's mistakes. The reported improvement is limited to the dataset's test split.

## Sources

- [cs.CL updates on arXiv.org](https://arxiv.org/abs/2610.27678)

---
Canonical: https://techandbusiness.org/newswire/CQQqmqCAsC0RLQwVXV_eh8
Published: 2026-10-21T05:05:43.844Z
Story chronology: 2026-10-21T04:00:00.000Z
Retrieved: 2026-10-25T06:20:10.601Z
Publisher: Tech & Business (techandbusiness.org)