IR-UWB Radar-Based Contactless Silent Speech Recognition with Attention-Enhanced Temporal Convolutional Networks

2025/09/30 by Lee, Sunghwa, Yu, Jaewon
#Audio and Speech Processing (eess.AS) #FOS: Electrical engineering #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2509.26409

Abstract

Silent speech recognition (SSR) is a technology that recognizes speech content from non-acoustic speech-related biosignals. This paper utilizes an attention-enhanced temporal convolutional network architecture for contactless IR-UWB radar-based SSR, leveraging deep learning to learn discriminative representations directly from minimally processed radar signals. The architecture integrates temporal convolutions with self-attention and squeeze-and-excitation mechanisms to capture articulatory patterns. Evaluated on a 50-word recognition task using leave-one-session-out cross-validation, our approach achieves an average test accuracy of 91.1% compared to 74.0% for the conventional hand-crafted feature method, demonstrating significant improvement through end-to-end learning.

Citations

• An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
• Squeeze-and-Excitation Networks
• Attention Is All You Need
• Deep Residual Learning for Image Recognition

Related

• End-to-end Silent Speech Recognition with Acoustic Sensing
• Advancing Speech Recognition With No Speech Or With Noisy Speech
• A Cross-Modal Approach to Silent Speech with LLM-Enhanced Recognition
• A Novel Task-Oriented Text Corpus in Silent Speech Recognition and its Natural Language Generation Construction Method
• Continuous Silent Speech Recognition using EEG