Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lee, Sunghwa, Yu, Jaewon
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2509.26409
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916980348420096
author Lee, Sunghwa
Yu, Jaewon
author_facet Lee, Sunghwa
Yu, Jaewon
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_26409
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle IR-UWB Radar-Based Contactless Silent Speech Recognition with Attention-Enhanced Temporal Convolutional Networks
Lee, Sunghwa
Yu, Jaewon
Audio and Speech Processing
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.
title IR-UWB Radar-Based Contactless Silent Speech Recognition with Attention-Enhanced Temporal Convolutional Networks
topic Audio and Speech Processing
url https://arxiv.org/abs/2509.26409