用雷达信号实现无接触无声语音识别，准确率达91.1%。
IR-UWB Radar-Based Contactless Silent Speech Recognition with Attention-Enhanced Temporal Convolutional Networks
- 结合时序卷积与注意力机制，直接从原始雷达信号学习特征。
- 在50词识别任务中准确率91.1%，远超传统手工特征方法的74.0%。
- 适合关注无接触生物信号识别与智能交互的研究者。
无声语音识别（SSR）是一种通过非声学语音相关生物信号识别语音内容的技术。本文提出一种基于注意力增强时序卷积网络的无接触红外超宽带（IR-UWB）雷达无声语音识别方法，利用深度学习直接从少量预处理的雷达信号中学习判别性表征。该架构融合时序卷积、自注意力与挤压-激励机制，有效捕捉发音动作模式。在包含50个词汇的识别任务上，采用留一会话交叉验证，本方法平均测试准确率达91.1%，显著优于传统手工特征方法的74.0%，验证了端到端学习的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。