Spoken language identification based on the enhanced self-adjusting extreme learning machine approach

Musatafa Abbas Abbood Albadr, Sabrina Tiun, Fahad Taha AL-Dhief, Mahmoud A.M. Sammour

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Spoken Language Identification (LID) is the process of determining and classifying natural language from a given content and dataset. Typically, data must be processed to extract useful features to perform LID. The extracting features for LID, based on literature, is a mature process where the standard features for LID have already been developed using Mel-Frequency Cepstral Coefficients (MFCC), Shifted Delta Cepstral (SDC), the Gaussian Mixture Model (GMM) and ending with the i-vector based framework. However, the process of learning based on extract features remains to be improved (i.e. optimised) to capture all embedded knowledge on the extracted features. The Extreme Learning Machine (ELM) is an effective learning model used to perform classification and regression analysis and is extremely useful to train a single hidden layer neural network. Nevertheless, the learning process of this model is not entirely effective (i.e. optimised) due to the random selection of weights within the input hidden layer. In this study, the ELM is selected as a learning model for LID based on standard feature extraction. One of the optimisation approaches of ELM, the Self-Adjusting Extreme Learning Machine (SA-ELM) is selected as the benchmark and improved by altering the selection phase of the optimisation process. The selection process is performed incorporating both the Split-Ratio and K-Tournament methods, the improved SA-ELM is named Enhanced Self-Adjusting Extreme Learning Machine (ESA-ELM). The results are generated based on LID with the datasets created from eight different languages. The results of the study showed excellent superiority relating to the performance of the Enhanced Self-Adjusting Extreme Learning Machine LID (ESA-ELM LID) compared with the SA-ELM LID, with ESA-ELM LID achieving an accuracy of 96.25%, as compared to the accuracy of SA-ELM LID of only 95.00%.

Original languageEnglish
Article numbere0194770
JournalPLoS One
Volume13
Issue number4
DOIs
Publication statusPublished - 1 Apr 2018

Fingerprint

artificial intelligence
Learning systems
Identification (control systems)
Language
learning
Learning
Machine Learning
Benchmarking
extracts
Regression analysis
Feature extraction
neural networks
regression analysis
Neural networks
Regression Analysis

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

Spoken language identification based on the enhanced self-adjusting extreme learning machine approach. / Albadr, Musatafa Abbas Abbood; Tiun, Sabrina; AL-Dhief, Fahad Taha; Sammour, Mahmoud A.M.

In: PLoS One, Vol. 13, No. 4, e0194770, 01.04.2018.

Research output: Contribution to journalArticle

Albadr, Musatafa Abbas Abbood ; Tiun, Sabrina ; AL-Dhief, Fahad Taha ; Sammour, Mahmoud A.M. / Spoken language identification based on the enhanced self-adjusting extreme learning machine approach. In: PLoS One. 2018 ; Vol. 13, No. 4.
@article{9ca86b481cf846bc8475d2a71ec4bb46,
title = "Spoken language identification based on the enhanced self-adjusting extreme learning machine approach",
abstract = "Spoken Language Identification (LID) is the process of determining and classifying natural language from a given content and dataset. Typically, data must be processed to extract useful features to perform LID. The extracting features for LID, based on literature, is a mature process where the standard features for LID have already been developed using Mel-Frequency Cepstral Coefficients (MFCC), Shifted Delta Cepstral (SDC), the Gaussian Mixture Model (GMM) and ending with the i-vector based framework. However, the process of learning based on extract features remains to be improved (i.e. optimised) to capture all embedded knowledge on the extracted features. The Extreme Learning Machine (ELM) is an effective learning model used to perform classification and regression analysis and is extremely useful to train a single hidden layer neural network. Nevertheless, the learning process of this model is not entirely effective (i.e. optimised) due to the random selection of weights within the input hidden layer. In this study, the ELM is selected as a learning model for LID based on standard feature extraction. One of the optimisation approaches of ELM, the Self-Adjusting Extreme Learning Machine (SA-ELM) is selected as the benchmark and improved by altering the selection phase of the optimisation process. The selection process is performed incorporating both the Split-Ratio and K-Tournament methods, the improved SA-ELM is named Enhanced Self-Adjusting Extreme Learning Machine (ESA-ELM). The results are generated based on LID with the datasets created from eight different languages. The results of the study showed excellent superiority relating to the performance of the Enhanced Self-Adjusting Extreme Learning Machine LID (ESA-ELM LID) compared with the SA-ELM LID, with ESA-ELM LID achieving an accuracy of 96.25{\%}, as compared to the accuracy of SA-ELM LID of only 95.00{\%}.",
author = "Albadr, {Musatafa Abbas Abbood} and Sabrina Tiun and AL-Dhief, {Fahad Taha} and Sammour, {Mahmoud A.M.}",
year = "2018",
month = "4",
day = "1",
doi = "10.1371/journal.pone.0194770",
language = "English",
volume = "13",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "4",

}

TY - JOUR

T1 - Spoken language identification based on the enhanced self-adjusting extreme learning machine approach

AU - Albadr, Musatafa Abbas Abbood

AU - Tiun, Sabrina

AU - AL-Dhief, Fahad Taha

AU - Sammour, Mahmoud A.M.

PY - 2018/4/1

Y1 - 2018/4/1

N2 - Spoken Language Identification (LID) is the process of determining and classifying natural language from a given content and dataset. Typically, data must be processed to extract useful features to perform LID. The extracting features for LID, based on literature, is a mature process where the standard features for LID have already been developed using Mel-Frequency Cepstral Coefficients (MFCC), Shifted Delta Cepstral (SDC), the Gaussian Mixture Model (GMM) and ending with the i-vector based framework. However, the process of learning based on extract features remains to be improved (i.e. optimised) to capture all embedded knowledge on the extracted features. The Extreme Learning Machine (ELM) is an effective learning model used to perform classification and regression analysis and is extremely useful to train a single hidden layer neural network. Nevertheless, the learning process of this model is not entirely effective (i.e. optimised) due to the random selection of weights within the input hidden layer. In this study, the ELM is selected as a learning model for LID based on standard feature extraction. One of the optimisation approaches of ELM, the Self-Adjusting Extreme Learning Machine (SA-ELM) is selected as the benchmark and improved by altering the selection phase of the optimisation process. The selection process is performed incorporating both the Split-Ratio and K-Tournament methods, the improved SA-ELM is named Enhanced Self-Adjusting Extreme Learning Machine (ESA-ELM). The results are generated based on LID with the datasets created from eight different languages. The results of the study showed excellent superiority relating to the performance of the Enhanced Self-Adjusting Extreme Learning Machine LID (ESA-ELM LID) compared with the SA-ELM LID, with ESA-ELM LID achieving an accuracy of 96.25%, as compared to the accuracy of SA-ELM LID of only 95.00%.

AB - Spoken Language Identification (LID) is the process of determining and classifying natural language from a given content and dataset. Typically, data must be processed to extract useful features to perform LID. The extracting features for LID, based on literature, is a mature process where the standard features for LID have already been developed using Mel-Frequency Cepstral Coefficients (MFCC), Shifted Delta Cepstral (SDC), the Gaussian Mixture Model (GMM) and ending with the i-vector based framework. However, the process of learning based on extract features remains to be improved (i.e. optimised) to capture all embedded knowledge on the extracted features. The Extreme Learning Machine (ELM) is an effective learning model used to perform classification and regression analysis and is extremely useful to train a single hidden layer neural network. Nevertheless, the learning process of this model is not entirely effective (i.e. optimised) due to the random selection of weights within the input hidden layer. In this study, the ELM is selected as a learning model for LID based on standard feature extraction. One of the optimisation approaches of ELM, the Self-Adjusting Extreme Learning Machine (SA-ELM) is selected as the benchmark and improved by altering the selection phase of the optimisation process. The selection process is performed incorporating both the Split-Ratio and K-Tournament methods, the improved SA-ELM is named Enhanced Self-Adjusting Extreme Learning Machine (ESA-ELM). The results are generated based on LID with the datasets created from eight different languages. The results of the study showed excellent superiority relating to the performance of the Enhanced Self-Adjusting Extreme Learning Machine LID (ESA-ELM LID) compared with the SA-ELM LID, with ESA-ELM LID achieving an accuracy of 96.25%, as compared to the accuracy of SA-ELM LID of only 95.00%.

UR - http://www.scopus.com/inward/record.url?scp=85045878408&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045878408&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0194770

DO - 10.1371/journal.pone.0194770

M3 - Article

C2 - 29672546

AN - SCOPUS:85045878408

VL - 13

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 4

M1 - e0194770

ER -