Authors:
Sandipan Dhar
1
;
Anuvab Sen
2
;
Aritra Bandyopadhyay
3
;
Nanda Jana
1
;
Arjun Ghosh
1
and
Zahra Sarayloo
4
Affiliations:
1
Computer Science and Engineering, National Institute of Technology, Durgapur, West Bengal, India
;
2
Electronics and Telecommunication, Indian Institute of Engineering Science and Technology, Shibpur, Howrah, India
;
3
Computer Science and Technology, Indian Institute of Engineering Science and Technology, Shibpur, Howrah, India
;
4
School of Computer Science, University of Waterloo, Ontario, Canada
Keyword(s):
Differential Evolution Algorithm, Genetic Algorithm, Convolutional Neural Network, Hyper-parameters Selection, Meta-heuristics, Speech Command Recognition, Deep Learning.
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.