Hello Edge: Keyword Spotting on Microcontrollers

Code

• github.com/ARM-software/ML-KWS-for-MCU
  OfficialIn papertf★ 0
• github.com/Jaskaran197/KWS-TF-MCU
  tf★ 0
• github.com/Paulonso/ML-KWS-for-MCU
  tf★ 0
• github.com/magahub/KWS-ARM
  tf★ 0
• github.com/UT2UH/ML-KWS-for-ESP32
  tf★ 0
• github.com/hustxsl/C-ML-KWS-for-MCU
  tf★ 0
• github.com/google-research/google-research/tree/master/kws_streaming
  tf★ 0
• github.com/fracorti/reds
  tf★ 0
• github.com/widzemin/audio_project
  tf★ 0
• github.com/Paulonso/ARM-software
  tf★ 0

Abstract

Keyword spotting (KWS) is a critical component for enabling speech based user interactions on smart devices. It requires real-time response and high accuracy for good user experience. Recently, neural networks have become an attractive choice for KWS architecture because of their superior accuracy compared to traditional speech processing algorithms. Due to its always-on nature, KWS application has highly constrained power budget and typically runs on tiny microcontrollers with limited memory and compute capability. The design of neural network architecture for KWS must consider these constraints. In this work, we perform neural network architecture evaluation and exploration for running KWS on resource-constrained microcontrollers. We train various neural network architectures for keyword spotting published in literature to compare their accuracy and memory/compute requirements. We show that it is possible to optimize these neural network architectures to fit within the memory and compute constraints of microcontrollers without sacrificing accuracy. We further explore the depthwise separable convolutional neural network (DS-CNN) and compare it against other neural network architectures. DS-CNN achieves an accuracy of 95.4%, which is ~10% higher than the DNN model with similar number of parameters.

Tasks

Benchmark Results

Reproductions