Encoder-Decoder Architectures for Silent Speech Recognition based on High-density Surface Electromyogram

Silent speech based on surface electromyogram(sEMG) has become an important interaction method. However, existing systems are highly dependent on time-alignment data, which is not conducive to the wide application of silent speech recognition (SSR) systems. In this study, we propose a convolutional...

Full description

Saved in:
Bibliographic Details
Published in:2022 International Conference on Advanced Robotics and Mechatronics (ICARM) pp. 760 - 763
Main Authors: Chen, Xi, Zhang, Xu, Chen, Xiang, Chen, Xun
Format: Conference Proceeding
Language:English
Published: IEEE 09.07.2022
Subjects:
Electrodes
Error analysis
Face recognition
Mechatronics
Memory architecture
Speech recognition
Training data
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Silent speech based on surface electromyogram(sEMG) has become an important interaction method. However, existing systems are highly dependent on time-alignment data, which is not conducive to the wide application of silent speech recognition (SSR) systems. In this study, we propose a convolutional Long Short-Term Memory-based encoder-decoder architecture to characterize and decode silent speech without time-alignment training data. The encoder can map the sEMG feature maps into a fixed-length feature vector, and the decoder can decode this vector back to the target sequence. To verify the effectiveness of the proposed method, the experimental data of 33 utterances from 7 subjects were collected from high-density electrode arrays with 64 channels from face and neck muscles. The performance of the proposed method was superior to the benchmark LSTM-based encoder-decoder architecture both on word error rate and utterance classification accuracy. These findings of this work indicate that the proposed method has the potential to achieve a rapid establishment of SSR system.
DOI:10.1109/ICARM54641.2022.9959417