Hardware Aware Training for Efficient Keyword Spotting on General Purpose and Specialized Hardware

SRAM for error-tolerant applications with dynamic energy-quality management in 28 nm CMOS

Fabio Frustaci, Mahmood Khayatzadeh, David Blaauw, Dennis Sylvester, and Massimo Alioto · 2015

Earlier work this paper cites.

A 65 nm 1.0 V 1.84 ns Silicon-on-Thin-Box (SOTB) embedded SRAM with 13.72 nW/Mbit standby power for smart IoT

Makoto Yabuuchi, Koji Nii, Shinji Tanaka, Yoshihiro Shinozaki, Yoshiki Yamamoto, Takumi Hasegawa, Hiroki Shinkawata, and Shiro Kamohara · 2017

Earlier work this paper cites.

Laika: A 5uW programmable LSTM accelerator for always-on keyword spotting in 65nm CMOS

J. S. P. Giraldo and M. Verhelst · 2018

Earlier work this paper cites.

SpiNNaker2 - Towards extremely efficient digital neuromorphics and multi-scale brain emulation

Sebastian Höppner and Christian Mayr · 2018

Earlier work this paper cites.

Speech Commands: A dataset for limited-vocabulary speech recognition

Original

Pete Warden · 2018

Earlier work this paper cites.

How to achieve world-leading energy efficiency using 22fdx with adaptive body biasing on an arm cortex-m4 iot soc

S. Höppner, H. Eisenreich, D. Walter, U. Steeb, A. S. Clifford Dmello, R. Sinkwitz, H. Bauer, A. Oefelein, F. Schraut, J. Schreiter, R. Niebsch, S. Scherzer, U. Hensel, J. Winkler, and M. Orgis · 2019

Earlier work this paper cites.

Legendre Memory Units: Continuous-time representation in recurrent neural networks

Aaron R. Voelker, Ivana Kajić, and Chris Eliasmith · 2019

Earlier work this paper cites.

Cortex-M4

ARM · 2020

Cited alongside, same era.

Micronets: Neural network architectures for deploying tinyml applications on commodity microcontrollers, 2020

Colby Banbury, Chuteng Zhou, Igor Fedorov, Ramon Matas Navarro, Urmish Thakker, Dibakar Gope, Vijay Janapa Reddi, Matthew Mattina, and Paul N. Whatmough · 2020

Cited alongside, same era.

Vocell: A 65-nm speech-triggered wake-up SoC for 10- μ \mu W keyword spotting and speaker verification

J. S. P. Giraldo, S. Lauwereins, K. Badami, and M. Verhelst · 2020

Cited alongside, same era.

The Speed and Power Advantage of a Purpose-Built Neural Compute Engine

Jeremy Holleman · 2020

Cited alongside, same era.

Small-footprint keyword spotting with multi-scale temporal convolution, 2020

Ximin Li, Xiaodong Wei, and Xiaowei Qin · 2020

Cited alongside, same era.

Syntiant NDP101 Microprocessor Receives Linley Group’s Analysts’ Choice Award

14.1 a 510nW 0.41V low-memory low-computation keyword-spotting chip using serial FFT-based MFCC and binarized depthwise separable convolutional neural network in 28nm CMOS

W. Shan, M. Yang, J. Xu, Y. Lu, S. Zhang, T. Wang, J. Yang, L. Shi, and M. Seok · 2020

Closest in time.

Always-on, sub-300-nW, event-driven spiking neural network based on spike-driven clock-generation and clock- and power-gating for an ultra-low-power intelligent device

Original

Dewei Wang, P. Chundi, S. Kim, Minhao Yang, J. P. Cerqueira, Joonsung Kang, Seungchul Jung, and Mingoo Seok · 2020

Closest in time.

Yosys Open SYnthesis Suite

Clifford Wolf · 2020

Closest in time.

TinySpeech: Attention condensers for deep speech recognition neural networks on edge devices

Original

Alexander Wong, Mahmoud Famouri, Maya Pavlova, and Siddharth Surana · 2020

Closest in time.

TinySpeech: Attention condensers for deep speech recognition neural networks on edge devices