How speech commands recognition on ESP32 actually works?

Описание

This is a follow-up to the previous "Train your own speech commands model in 10 minutes, and run it on ESP32 with MicroPython" video, where I introduced a way to easily try out speech commands recognition on ESP32. If you would like to learn more details on both model inference and model training, check out this video!

References used in the video:
Neural Network on Microcontroller: https://github.com/majianjia/nnom
Build MicroPython for ESP32: https://github.com/micropython/micropython/blob/master/ports/esp32/README.md
Transfer Learning using TensorFlow.js: https://www.tensorflow.org/js/tutorials/transfer/audio_recognizer
Google Speech Commands Dataset: https://ai.googleblog.com/2017/08/launching-speech-commands-dataset.html