Differential Evolution Algorithm Based Hyper-Parameters Selection of Convolutional Neural Network for Speech Command Recognition

Sandipan Dhar, Anuvab Sen, Aritra Bandyopadhyay, Nanda Jana, Arjun Ghosh, Zahra Sarayloo

2023

Abstract

Speech Command Recognition (SCR), which deals with identification of short uttered speech commands, is crucial for various applications, including IoT devices and assistive technology. Despite the promise shown by Convolutional Neural Networks (CNNs) in SCR tasks, their efficacy relies heavily on hyperparameter selection, which is typically laborious and time-consuming when done manually. This paper introduces a hyperparameter selection method for CNNs based on the Differential Evolution (DE) algorithm, aiming to enhance performance in SCR tasks. Training and testing with the Google Speech Command (GSC) dataset, the proposed approach showed effectiveness in classifying speech commands. Moreover, a comparative analysis with Genetic Algorithm-based selections and other deep CNN (DCNN) models highlighted the efficiency of the proposed DE algorithm in hyperparameter selection for CNNs in SCR tasks.

Paper Citation

in Harvard Style

Dhar S., Sen A., Bandyopadhyay A., Jana N., Ghosh A. and Sarayloo Z. (2023). Differential Evolution Algorithm Based Hyper-Parameters Selection of Convolutional Neural Network for Speech Command Recognition. In Proceedings of the 15th International Joint Conference on Computational Intelligence - Volume 1: ECTA; ISBN 978-989-758-674-3, SciTePress, pages 315-322. DOI: 10.5220/0012251500003595

in Bibtex Style

@conference{ecta23,
author={Sandipan Dhar and Anuvab Sen and Aritra Bandyopadhyay and Nanda Jana and Arjun Ghosh and Zahra Sarayloo},
title={Differential Evolution Algorithm Based Hyper-Parameters Selection of Convolutional Neural Network for Speech Command Recognition},
booktitle={Proceedings of the 15th International Joint Conference on Computational Intelligence - Volume 1: ECTA},
year={2023},
pages={315-322},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012251500003595},
isbn={978-989-758-674-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computational Intelligence - Volume 1: ECTA
TI - Differential Evolution Algorithm Based Hyper-Parameters Selection of Convolutional Neural Network for Speech Command Recognition
SN - 978-989-758-674-3
AU - Dhar S.
AU - Sen A.
AU - Bandyopadhyay A.
AU - Jana N.
AU - Ghosh A.
AU - Sarayloo Z.
PY - 2023
SP - 315
EP - 322
DO - 10.5220/0012251500003595
PB - SciTePress