Cover Image

Wake word and speech recognition application on edge device: a case of improving the electric wheelchair / Low Jian He ... [et al.]

Edge devices play an ever-increasing role as to reduce latency, improve efficiency and adapt simplicity. However, their lower processing capabilities compared to traditional setup means that their usage are also limited. This research explores the possibility of implementing both wake word and speec...

Full description

Saved in:
Bibliographic Details
Main Authors: Low, Jian He, Fadhlullah, Solahuddin Yusuf, Kamarulazizi, Khadijah, Abdullah, Samihah, Abdul Hamid, Shabinar
Format: Article
Language:English
Published: UiTM Press 2024
Subjects:
Applications of electronics
Online Access:https://ir.uitm.edu.my/id/eprint/94745/1/94745.pdf
https://ir.uitm.edu.my/id/eprint/94745/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.uitm.ir.94745
record_format eprints
spelling my.uitm.ir.947452024-05-07T09:04:28Z https://ir.uitm.edu.my/id/eprint/94745/ Wake word and speech recognition application on edge device: a case of improving the electric wheelchair / Low Jian He ... [et al.] jeesr Low, Jian He Fadhlullah, Solahuddin Yusuf Kamarulazizi, Khadijah Abdullah, Samihah Abdul Hamid, Shabinar Applications of electronics Edge devices play an ever-increasing role as to reduce latency, improve efficiency and adapt simplicity. However, their lower processing capabilities compared to traditional setup means that their usage are also limited. This research explores the possibility of implementing both wake word and speech recognition on an edge device. The proposed wake word system, which is for voice activation, is developed based on the LSTM Neural Network model. The model is trained, modelled, and evaluated to respond to the wake word of “Hey SellTron”. As for the speech recognition (voice command) system, Google Speech API was selected to recognize standard directional commands (left, right, forwards, backwards), as well as the new conceptual locational commands (“go to kitchen”, “go to bedroom”, etc.). To prove the feasibility of the developed system, these two features were integrated into an edge device on a mobile platform; representing a conceptual mini wheelchair ‘prototype’ due to project constraints. Evaluations showed that the prototype was able to activate and respond to voice commands correctly with over 80% accuracy in low ambient noise (<50dB). UiTM Press 2024-04 Article PeerReviewed text en https://ir.uitm.edu.my/id/eprint/94745/1/94745.pdf Wake word and speech recognition application on edge device: a case of improving the electric wheelchair / Low Jian He ... [et al.]. (2024) Journal of Electrical and Electronic Systems Research (JEESR) <https://ir.uitm.edu.my/view/publication/Journal_of_Electrical_and_Electronic_Systems_Research_=28JEESR=29/>, 24 (1): 13. pp. 80-88. ISSN 1985-5389
institution Universiti Teknologi Mara
building Tun Abdul Razak Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Mara
content_source UiTM Institutional Repository
url_provider http://ir.uitm.edu.my/
language English
topic Applications of electronics
spellingShingle Applications of electronics
Low, Jian He
Fadhlullah, Solahuddin Yusuf
Kamarulazizi, Khadijah
Abdullah, Samihah
Abdul Hamid, Shabinar
Wake word and speech recognition application on edge device: a case of improving the electric wheelchair / Low Jian He ... [et al.]
description Edge devices play an ever-increasing role as to reduce latency, improve efficiency and adapt simplicity. However, their lower processing capabilities compared to traditional setup means that their usage are also limited. This research explores the possibility of implementing both wake word and speech recognition on an edge device. The proposed wake word system, which is for voice activation, is developed based on the LSTM Neural Network model. The model is trained, modelled, and evaluated to respond to the wake word of “Hey SellTron”. As for the speech recognition (voice command) system, Google Speech API was selected to recognize standard directional commands (left, right, forwards, backwards), as well as the new conceptual locational commands (“go to kitchen”, “go to bedroom”, etc.). To prove the feasibility of the developed system, these two features were integrated into an edge device on a mobile platform; representing a conceptual mini wheelchair ‘prototype’ due to project constraints. Evaluations showed that the prototype was able to activate and respond to voice commands correctly with over 80% accuracy in low ambient noise (<50dB).
format Article
author Low, Jian He
Fadhlullah, Solahuddin Yusuf
Kamarulazizi, Khadijah
Abdullah, Samihah
Abdul Hamid, Shabinar
author_facet Low, Jian He
Fadhlullah, Solahuddin Yusuf
Kamarulazizi, Khadijah
Abdullah, Samihah
Abdul Hamid, Shabinar
author_sort Low, Jian He
title Wake word and speech recognition application on edge device: a case of improving the electric wheelchair / Low Jian He ... [et al.]
title_short Wake word and speech recognition application on edge device: a case of improving the electric wheelchair / Low Jian He ... [et al.]
title_full Wake word and speech recognition application on edge device: a case of improving the electric wheelchair / Low Jian He ... [et al.]
title_fullStr Wake word and speech recognition application on edge device: a case of improving the electric wheelchair / Low Jian He ... [et al.]
title_full_unstemmed Wake word and speech recognition application on edge device: a case of improving the electric wheelchair / Low Jian He ... [et al.]
title_sort wake word and speech recognition application on edge device: a case of improving the electric wheelchair / low jian he ... [et al.]
publisher UiTM Press
publishDate 2024
url https://ir.uitm.edu.my/id/eprint/94745/1/94745.pdf
https://ir.uitm.edu.my/id/eprint/94745/
_version_ 1800100625280663552
score 13.211869

Similar Items