Vocell: A 65-nm Speech-Triggered Wake-Up SoC for 10-$\mu$ W Keyword Spotting and Speaker Verification
Juan Sebastian Piedrahita Giraldo, Steven Lauwereins, Komail Badami, Marian Verhelst
Abstract
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) memoryand power-optimized accelerators, ultra-low power is achieved while maintaining high accuracy for speech recognition tasks. The 65-nm implementation achieves 18.3-μW worst case power consumption or 10.6-μW power for typical real-time scenarios, 10× below state of the art (SoA).