A Sub-400-nW Real-Time Event-Driven Spectrogram Extraction Unit in 28-nm FD-SOI CMOS for Keyword Spotting Application
- 8 November 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Solid-State Circuits
- Vol. 60 (6) , 2060-2071
Abstract
Considering the power-hungry nature of speech processing, a keyword spotting (KWS) unit, used to detect multiple spoken words, is often integrated as a front-end layer. KWS systems are always active, and thus, it is extremely important to optimize the devoted power budget. In this context, this article presents a programmable low-power event-driven real-time spectrogram extraction unit tested for the KWS application. This chip, fabricated in 28-nm FD-SOI CMOS technology, has been combined with a software-defined convolutional neural network to demonstrate the recognition of 11 audio classes (ten keywords $+$ background $+$ unknown) with an accuracy equal to 87.9% and an activity-dependent power consumption measured at 391.6 nW, for a 12-keyword/min average speech rate.Keywords
This publication has 19 references indexed in Scilit:
- Low-Power Event-Driven Spectrogram Extractor for Multiple Keyword Spotting: A proof of concept2023
- Ultra-Low-Power and Compact-Area Analog Audio Feature Extraction Based on Time-Mode Analog Filterbank Interpolation and Time-Mode Analog RectificationIEEE Journal of Solid-State Circuits, 2022
- A 23-μW Keyword Spotting IC With Ring-Oscillator-Based Time-Domain Feature ExtractionIEEE Journal of Solid-State Circuits, 2022
- Event-Driven Continuous-Time Feature Extraction for Ultra Low-Power Audio Keyword Spotting2021
- A Software-Defined Always-On System With 57–75-nW Wake-Up Function Using Asynchronous Clock-Free Pipelined Event-Driven Architecture and Time-Shielding Level-Crossing ADCIEEE Journal of Solid-State Circuits, 2021
- A 510-nW Wake-Up Keyword-Spotting Chip Using Serial-FFT-Based MFCC and Binarized Depthwise Separable CNN in 28-nm CMOSIEEE Journal of Solid-State Circuits, 2020
- A Wide Tuning Range Delay Element for Event-Driven Processing of Low-Frequency Signals in 28-nm FD-SOI CMOSIEEE Solid-State Circuits Letters, 2020
- Vocell: A 65-nm Speech-Triggered Wake-Up SoC for 10-$\mu$ W Keyword Spotting and Speaker VerificationIEEE Journal of Solid-State Circuits, 2020
- Pseudo Asynchronous Level Crossing adc for ecg Signal AcquisitionIEEE Transactions on Biomedical Circuits and Systems, 2017
- A Continuous-Time ADC/DSP/DAC System With No Clock and With Activity-Dependent Power DissipationIEEE Journal of Solid-State Circuits, 2008