A 0.81mm2 740µW Real-Time Speech Enhancement Processor Using Multiplier-Less PE Arrays for Hearing Aids in 28nm CMOS

📋 论文概要

该论文提出了一款用于助听器的实时语音增强处理器，采用无乘法器处理单元（PE）阵列，在28nm CMOS工艺下实现0.81mm²面积和740µW功耗。通过算法与硬件协同优化，解决了深度学习模型在可穿戴设备中计算复杂度和功耗过高的问题。

💡 主要创新点

• 采用无乘法器PE阵列设计，大幅降低计算功耗和面积开销。
• 实现实时语音增强处理，满足助听器低功耗、小尺寸的严格约束。
• 通过算法与硬件联合优化，在保持语音增强质量的同时显著提升能效。

🏷 关键词

📄 原文摘要

Speech enhancement (SE) is a task to improve voice quality and intelligibility by removing noise from the audio, which is widely adopted in hearing assistive devices. Hearing aids are generally worn in or behind the ear, requiring real-time processing with a limited power budget. Deep learning-based algorithms provide excellent SE quality, but their large model size and high computational complexity make them unsuitable for wearable hearing assistive devices. Recent hardware-oriented works mitigate these issues through algorithm and hardware optimization [1-3]. Nonetheless, they exhibit inferior SE performance relative to state-of-the-art models or rely on large neural network models, limiting overall processing efficiency. This paper presents an end-to-end SE system that delivers high-quality SE with low power consumption and small area, while meeting realtime processing constraints. Our main contributions are: 1) an importance-aware neural

👥 作者与机构

Sungjin Park, Sunwoo Lee, Jeongwoo Park, Hyeong-Seok Choi, Dongsuk Jeon

Seoul National University, Seoul, Korea