A comparative review of dynamic neural networks and hidden Markov model methods for mobile on-device speech recognition

Mustafa, MK, Allen, T ORCID: https://orcid.org/0000-0001-6228-0237 and Appiah, K ORCID: https://orcid.org/0000-0002-9480-0679, 2017. A comparative review of dynamic neural networks and hidden Markov model methods for mobile on-device speech recognition. Neural Computing and Applications. ISSN 0941-0643

Preview

Text 9029_Allen.pdf - Published version Download (782kB) | Preview

Abstract

The adoption of high-accuracy speech recognition algorithms without an effective evaluation of their impact on the target computational resource is impractical for mobile and embedded systems. In this paper, techniques are adopted to minimise the required computational resource for an effective mobile-based speech recognition system. A Dynamic Multi-Layer Perceptron speech recognition technique, capable of running in real time on a state-of-the-art mobile device, has been introduced. Even though a conventional hidden Markov model when applied to the same dataset slightly outperformed our approach, its processing time is much higher. The Dynamic Multi-layer Perceptron presented here has an accuracy level of 96.94% and runs significantly faster than similar techniques.

Item Type:	Journal article
Publication Title:	Neural Computing and Applications
Creators:	Mustafa, M.K., Allen, T. and Appiah, K.
Publisher:	Springer
Date:	4 June 2017
ISSN:	0941-0643
Identifiers:	Number Type 10.1007/s00521-017-3028-2 DOI 3028 Publisher Item Identifier
Rights:	This article is distributed under the terms of the Creative Commons Attribution 4.0 International License
Divisions:	Schools > School of Science and Technology
Record created by:	Jonathan Gallacher
Date Added:	31 Aug 2017 15:47
Last Modified:	24 Nov 2021 11:09
URI:	https://irep.ntu.ac.uk/id/eprint/31512

Actions (login required)

Edit View

Statistics

Views

Downloads