ETD system

Electronic theses and dissertations repository

 

Tesi etd-04162018-154315


Thesis type
Tesi di laurea magistrale
Author
BENELLI, GIONATA
URN
etd-04162018-154315
Title
Artificial Intelligence applied to keyword spotting for low-power and memory constrained embedded device
Struttura
INGEGNERIA DELL'INFORMAZIONE
Corso di studi
EMBEDDED COMPUTING SYSTEMS
Commissione
relatore Prof. Fanucci, Luca
relatore Palla, Alessandro
Parole chiave
  • low-power
  • deep learning
  • artificial intelligence
  • keyword spotting
  • constrained devices
  • riconoscimento vocale
  • neural network
Data inizio appello
07/05/2018;
Consultabilità
parziale
Data di rilascio
07/05/2021
Riassunto analitico
Given a domotic installation based on the Internet of things paradigm, we would like to provide a Voice Wake up to enable hands-free interaction for a user with impaired mobility for increasing quality of life. <br>We focused on developing a keyword spotting system for constrained devices to enable a low-power voice interaction.<br> In order to meet the requirements we propose an architecture based on Deep Neural Network. We explore different options based on Convolutional Neural Network, and we propose a new architecture which gives an increase of over 5\% accuracy over standard Convolution architecture, with just a tenth of the total memory footprint if we compare it with previous research on Convolutional Neural Networks for embedded device. We also explore data-augmentations and pseudo-labeling as a way of increasing the robustness of the network without increasing size. Finally we test our implementation over a Raspberry Pi 3,obtaining a reduction of power consumption of over 50\% with respect to previous works, but with the same accuracy.
File