Ultrasensitive Textile Strain Sensors Redefine Wearable Silent Speech Interfaces with High Machine Learning Efficiency

TL;DR

This paper introduces a highly sensitive, comfortable textile-based silent speech interface that uses a graphene strain sensor and an efficient neural network to accurately decode speech with minimal energy and training data.

Contribution

It presents a novel textile choker with a graphene sensor and a lightweight neural network for real-time silent speech decoding, improving sensitivity and efficiency over existing methods.

Findings

Sensor sensitivity surpasses existing sensors by 420%.

Decoding accuracy reaches 95.25% for 20 words.

System reduces computational load by 90%.

Abstract

Our research presents a wearable Silent Speech Interface (SSI) technology that excels in device comfort, time-energy efficiency, and speech decoding accuracy for real-world use. We developed a biocompatible, durable textile choker with an embedded graphene-based strain sensor, capable of accurately detecting subtle throat movements. This sensor, surpassing other strain sensors in sensitivity by 420%, simplifies signal processing compared to traditional voice recognition methods. Our system uses a computationally efficient neural network, specifically a one-dimensional convolutional neural network with residual structures, to decode speech signals. This network is energy and time-efficient, reducing computational load by 90% while achieving 95.25% accuracy for a 20-word lexicon and swiftly adapting to new users and words with minimal samples. This innovation demonstrates a practical, sensitive, and precise wearable SSI suitable for daily communication applications.