Scholarlink

<p>Edge audio recognition demands extreme energy efficiency and noise resilience. Conventional separate denoising and recognition modules incur high overhead and latency, hindering deployment on resource-constrained edge devices. Inspired by biological audition, here we show a memristor-based neuromorphic system that monolithically integrates on-chip audio denoising and recognition. Our Pt/IGZO/SiN<sub>x</sub>/Ta memristor achieves a 19 mV biomimetic voltage and high endurance of 10<sup>6</sup> cycles. Fabricated into a uniform 1-kb crossbar array, the system supports partitioned processing: a volatile-switching denoising region enables real-time noise suppression, activating based on input signal strength without erasure steps, while a non-volatile region performs high-precision classification. This end-to-end solution attains 100% accuracy on 10-class audio signals (500 samples) after 15 training epochs with post-denoising, consuming 1.44 fJ per denoising operation, outperforming non-denoised approaches in convergence speed and robustness. Confusion matrices confirm &gt;90% class-specific accuracy under noise, establishing a pathway for miniaturized, energy-scalable edge hardware.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Biomimetic-voltage nitride-enhanced memristor arrays for femtojoule in-memory biosignal processing

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月6日

查看全文
  • Zijian Wang,
  • Zhejia Zhang,
  • Guobin Zhang,
  • Xuemeng Fan,
  • Pengtao Li,
  • Baicheng Zhu,
  • Yi Tong,
  • Panpan Zhang,
  • Dawei Gao,
  • Bin Yu,
  • Jiuren Zhou,
  • Qing Wan,
  • Yishu Zhang

摘要

Edge audio recognition demands extreme energy efficiency and noise resilience. Conventional separate denoising and recognition modules incur high overhead and latency, hindering deployment on resource-constrained edge devices. Inspired by biological audition, here we show a memristor-based neuromorphic system that monolithically integrates on-chip audio denoising and recognition. Our Pt/IGZO/SiNx/Ta memristor achieves a 19 mV biomimetic voltage and high endurance of 106 cycles. Fabricated into a uniform 1-kb crossbar array, the system supports partitioned processing: a volatile-switching denoising region enables real-time noise suppression, activating based on input signal strength without erasure steps, while a non-volatile region performs high-precision classification. This end-to-end solution attains 100% accuracy on 10-class audio signals (500 samples) after 15 training epochs with post-denoising, consuming 1.44 fJ per denoising operation, outperforming non-denoised approaches in convergence speed and robustness. Confusion matrices confirm >90% class-specific accuracy under noise, establishing a pathway for miniaturized, energy-scalable edge hardware.