Attention Bidirectional LSTM Networks Based Mime Speech Recognition Using sEMG Data

Feature Engineering Diagram: time domain and time-frequency domain

Abstract

Surface electromyography (sEMG) has been proven competent and reliable to recognize speech musculature movement patterns. In other words, we can understand what a person prepares to say by collecting sEMG signals around the mouth. Therefore, sEMG-based Mime Speech Recognition (MSR) is a potential technique for human-machine interaction within noisy surroundings as well as the application of helping dysarthric patients. In this paper, we introduce multi-layer Bidirectional Long Short-Term Memory (BLSTM) networks with attention mechanism as a classifier for MSR, and verify it in the data set collected by ourselves. Six-channel sEMG signals are firstly acquired from elaborately selected facial muscles. Short-time Fourier Transform (STFT) and Convolutional Neural Networks (CNN) are utilized to extract time-frequency domain feature maps, replacing the handcrafted features in classic methods. The second phase of recognition process lies in the designed classifier. This classification system achieves over 97% accuracy in the fourclass MSR task, significantly surpassing simple CNN and LSTM methods. Such result also indicates that excellent MSR results can be achieved without relying on handcrafted signal features.

Click the Slides button above to demo Academic’s Markdown slides feature.

Supplementary notes can be added here, including code and math.

Haohong Lin
Haohong Lin
Senior Undergraduate

My research interests include distributed robotics, mobile computing and programmable matter.

Related