Download PDFOpen PDF in browser

Implementation of Tiny Machine Learning Models on Arduino 33 – BLE for Gesture and Speech Recognition

EasyChair Preprint 8495

10 pagesDate: July 16, 2022

Abstract

.nd low power consumption, and it can easily integrate machine learning with virtually anything. It also has the benefit of increased security due to the local nature of computing. The benefit of using Arduino Nano 33 BLE sense is that it has a set of sensors embedded on the top, which gives us many options to try ideas without generating the circuit to such sensors in prototyping board. It features 3-axis accelerometer, 3- axis gyroscope and 3-axis magnetometer. The gesture recognition, provides an innovative approach nonverbal communication. It has wide applications in human-computer interaction and sign language. Here in the implementation of hand gesture recognition, TinyML model is trained and deployed from EdgeImpulse framework for hand gesture recognition and based on the hand movements, Arduino Nano 33 BLE device having 6- axis IMU can find out the direction of movement of hand. The Speech is a mode of communication. Speech recognition is a way the computer understands the statements or commands of human speech, which reacts accordingly. The main aim of speech recognition is to communicate between man and machine. Here in the implementation of speech recognition, TinyML model is trained and deployed from EdgeImpulse framework for speech recognition and based on the keyword pronounced by human, Arduino Nano 33 BLE device having built-in microphone can make an RGB LED glow like red, green or blue based on keyword pronounced. The results of each application are obtained and listed in the results section and given the analysis upon the results

Keyphrases: TinyML, gesture recognition, hardware implementation, machine learning, speech recognition

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
@booklet{EasyChair:8495,
  author    = {V Viswanatha and A. C Ramachandra and R Raghavendra Prasanna and Prem Chowdary Kakarla and Pj Viveka Simha and Nishant Mohan},
  title     = {Implementation of Tiny Machine Learning Models on Arduino 33 – BLE for Gesture and Speech Recognition},
  howpublished = {EasyChair Preprint 8495},
  year      = {EasyChair, 2022}}
Download PDFOpen PDF in browser