An automated speech recognition and feature selection approach based on improved Northern Goshawk optimization
Automatic speech recognition (ASR) approach is dependent on optimal speech feature extraction, which attempts to get a parametric depiction of an input speech signal. Feature extraction (FE) strategy combined with a feature selection (FS) approach should capture the most important features of the si...
Main Authors: | , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Institute of Advanced Engineering and Science
2024
|
Subjects: | |
Online Access: | https://ijai.iaescore.com/index.php/IJAI/article/view/22771 https://doi.org/10.11591/ijai.v13.i1.pp296-304 |
id |
ftjijai:oai:ojs.www.iaescore.com:article/22771 |
---|---|
record_format |
openpolar |
spelling |
ftjijai:oai:ojs.www.iaescore.com:article/22771 2024-04-07T07:54:50+00:00 An automated speech recognition and feature selection approach based on improved Northern Goshawk optimization Suryakumar, Santosh Kumar Hiremath, Bharathi S. Mohankumar, Nageswara Guptha 2024-03-01 application/pdf https://ijai.iaescore.com/index.php/IJAI/article/view/22771 https://doi.org/10.11591/ijai.v13.i1.pp296-304 eng eng Institute of Advanced Engineering and Science https://ijai.iaescore.com/index.php/IJAI/article/view/22771/13830 https://ijai.iaescore.com/index.php/IJAI/article/view/22771 doi:10.11591/ijai.v13.i1.pp296-304 Copyright (c) 2023 Institute of Advanced Engineering and Science http://creativecommons.org/licenses/by-sa/4.0 IAES International Journal of Artificial Intelligence (IJ-AI); Vol 13, No 1: March 2024; 296-304 2252-8938 2089-4872 10.11591/ijai.v13.i1 Machine Learning Optimization Automatic speech recognition Feature selection K-nearest neighbour Northern Goshawk optimization Opposition based learning info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion 2024 ftjijai https://doi.org/10.11591/ijai.v13.i1.pp296-30410.11591/ijai.v13.i1 2024-03-08T02:55:52Z Automatic speech recognition (ASR) approach is dependent on optimal speech feature extraction, which attempts to get a parametric depiction of an input speech signal. Feature extraction (FE) strategy combined with a feature selection (FS) approach should capture the most important features of the signal while discarding the rest. FS is a crucial process that can affect the pattern classification and recognition system's performance. In this research, we introduce a hybrid supervised learning using metaheuristic technique for optimum FE and FS termed Northern Goshawk optimization (NGO) and opposition-based learning (OBL). Pre-processing, feature extraction and selection, and recognition are the three steps of the proposed technique. The pre-processing is done first to lessen the amount of noise. In the FE stage, we extract features. The OBL-NGO method is used to pick the best collection of extracted characteristics. Finally, these optimised features are utilised to train the k-nearest neighbour (KNN) classifier, and the matching text is shown as the output based on these optimised characteristics of the provided input audio signal. The system's performance is outstanding, and the suggested OBL-NGO is best suited for ASR, according to the testing data. Article in Journal/Newspaper Northern Goshawk IAES International Journal of Artificial Intelligence (IJ-AI) |
institution |
Open Polar |
collection |
IAES International Journal of Artificial Intelligence (IJ-AI) |
op_collection_id |
ftjijai |
language |
English |
topic |
Machine Learning Optimization Automatic speech recognition Feature selection K-nearest neighbour Northern Goshawk optimization Opposition based learning |
spellingShingle |
Machine Learning Optimization Automatic speech recognition Feature selection K-nearest neighbour Northern Goshawk optimization Opposition based learning Suryakumar, Santosh Kumar Hiremath, Bharathi S. Mohankumar, Nageswara Guptha An automated speech recognition and feature selection approach based on improved Northern Goshawk optimization |
topic_facet |
Machine Learning Optimization Automatic speech recognition Feature selection K-nearest neighbour Northern Goshawk optimization Opposition based learning |
description |
Automatic speech recognition (ASR) approach is dependent on optimal speech feature extraction, which attempts to get a parametric depiction of an input speech signal. Feature extraction (FE) strategy combined with a feature selection (FS) approach should capture the most important features of the signal while discarding the rest. FS is a crucial process that can affect the pattern classification and recognition system's performance. In this research, we introduce a hybrid supervised learning using metaheuristic technique for optimum FE and FS termed Northern Goshawk optimization (NGO) and opposition-based learning (OBL). Pre-processing, feature extraction and selection, and recognition are the three steps of the proposed technique. The pre-processing is done first to lessen the amount of noise. In the FE stage, we extract features. The OBL-NGO method is used to pick the best collection of extracted characteristics. Finally, these optimised features are utilised to train the k-nearest neighbour (KNN) classifier, and the matching text is shown as the output based on these optimised characteristics of the provided input audio signal. The system's performance is outstanding, and the suggested OBL-NGO is best suited for ASR, according to the testing data. |
format |
Article in Journal/Newspaper |
author |
Suryakumar, Santosh Kumar Hiremath, Bharathi S. Mohankumar, Nageswara Guptha |
author_facet |
Suryakumar, Santosh Kumar Hiremath, Bharathi S. Mohankumar, Nageswara Guptha |
author_sort |
Suryakumar, Santosh Kumar |
title |
An automated speech recognition and feature selection approach based on improved Northern Goshawk optimization |
title_short |
An automated speech recognition and feature selection approach based on improved Northern Goshawk optimization |
title_full |
An automated speech recognition and feature selection approach based on improved Northern Goshawk optimization |
title_fullStr |
An automated speech recognition and feature selection approach based on improved Northern Goshawk optimization |
title_full_unstemmed |
An automated speech recognition and feature selection approach based on improved Northern Goshawk optimization |
title_sort |
automated speech recognition and feature selection approach based on improved northern goshawk optimization |
publisher |
Institute of Advanced Engineering and Science |
publishDate |
2024 |
url |
https://ijai.iaescore.com/index.php/IJAI/article/view/22771 https://doi.org/10.11591/ijai.v13.i1.pp296-304 |
genre |
Northern Goshawk |
genre_facet |
Northern Goshawk |
op_source |
IAES International Journal of Artificial Intelligence (IJ-AI); Vol 13, No 1: March 2024; 296-304 2252-8938 2089-4872 10.11591/ijai.v13.i1 |
op_relation |
https://ijai.iaescore.com/index.php/IJAI/article/view/22771/13830 https://ijai.iaescore.com/index.php/IJAI/article/view/22771 doi:10.11591/ijai.v13.i1.pp296-304 |
op_rights |
Copyright (c) 2023 Institute of Advanced Engineering and Science http://creativecommons.org/licenses/by-sa/4.0 |
op_doi |
https://doi.org/10.11591/ijai.v13.i1.pp296-30410.11591/ijai.v13.i1 |
_version_ |
1795671630243954688 |