The use of speech-triggered wake-up interfaces has grown significantly in the last few years for use in ubiquitous and mobile devices. Since these interfaces must always be active, power consumption is one of their primary design metrics. This article presents a complete mixed-signal system-on-chip, capable of directly interfacing to an analog microphone and performing keyword spotting (KWS) and speaker verification (SV), without any need for further external accesses. Through the use of: 1) an integrated single-chip digital-friendly design; b) hardware-aware algorithmic optimization; and c) memory- and power-optimized accelerators, ultra-low power is achieved while maintaining high accuracy for speech recognition tasks. The 65-nm implementation achieves 18.3- $\mu \text{W}$ worst case power consumption or 10.6- $\mu \text{W}$ power for typical real-time scenarios, $10\times $ below state of the art (SoA).

中文翻译：

---

Vocell：用于 10μW 关键字定位和说话人验证的 65-nm 语音触发唤醒 SoC

语音触发唤醒接口的使用在过去几年中显着增长，用于无处不在的移动设备。由于这些接口必须始终处于活动状态，因此功耗是其主要设计指标之一。本文介绍了一个完整的混合信号片上系统，能够直接连接到模拟麦克风并执行关键字识别 (KWS) 和扬声器验证 (SV)，无需进一步的外部访问。通过使用： 1）集成单片机数字友好设计；b) 硬件感知算法优化；c) 内存和功耗优化的加速器，实现了超低功耗，同时保持语音识别任务的高精度。65-nm 实现实现了 18.3- $\mu \text{W}$ 最坏情况下的功耗或 10.6- $\mu \text{W}$ 典型实时场景的电源， $10\times $ 低于最先进水平 (SoA)。