Artificial Neural Network (ANN) in a Small Dataset to determine Neutrality in the Pronunciation of English as a Foreign Language in Filipino Call Center Agents

Artificial Neural Networks (ANNs) have continued to be efficient models in solving classification problems. In this paper, we explore the use of an ANN with a small dataset to accurately classify whether Filipino call center agents’ pronunciations are neutral or not based on their employer’s standar...

Full description

Saved in:
Bibliographic Details
Main Authors: Fernandez, Proceso L, Jr, Baquirin, Rey Benjamin M
Format: text
Published: Archīum Ateneo 2018
Subjects:
Online Access:https://archium.ateneo.edu/discs-faculty-pubs/73
https://archium.ateneo.edu/cgi/viewcontent.cgi?article=1072&context=discs-faculty-pubs
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Ateneo De Manila University
id ph-ateneo-arc.discs-faculty-pubs-1072
record_format eprints
spelling ph-ateneo-arc.discs-faculty-pubs-10722020-05-06T08:04:13Z Artificial Neural Network (ANN) in a Small Dataset to determine Neutrality in the Pronunciation of English as a Foreign Language in Filipino Call Center Agents Fernandez, Proceso L, Jr Baquirin, Rey Benjamin M Artificial Neural Networks (ANNs) have continued to be efficient models in solving classification problems. In this paper, we explore the use of an ANN with a small dataset to accurately classify whether Filipino call center agents’ pronunciations are neutral or not based on their employer’s standards. Isolated utterances of the ten most commonly used words in the call center were recorded from eleven agents creating a dataset of 110 utterances. Two learning specialists were consulted to establish ground truths and Cohen’s Kappa was computed as 0.82, validating the reliability of the dataset. The first thirteen Mel-Frequency Cepstral Coefficients (MFCCs) were then extracted from each word and an ANN was trained with Ten-fold Stratified Cross Validation. Experimental results on the model recorded a classification accuracy of 89.60% supported by an overall F-Score of 0.92. 2018-01-01T08:00:00Z text application/pdf https://archium.ateneo.edu/discs-faculty-pubs/73 https://archium.ateneo.edu/cgi/viewcontent.cgi?article=1072&context=discs-faculty-pubs Department of Information Systems & Computer Science Faculty Publications Archīum Ateneo Automatic Speech Classification Artificial Intelligence Neural Networks Mel-Frequency Cepstral Coefficients Machine Learning Artificial Intelligence and Robotics Computer Sciences
institution Ateneo De Manila University
building Ateneo De Manila University Library
country Philippines
collection archium.Ateneo Institutional Repository
topic Automatic Speech Classification
Artificial Intelligence
Neural Networks
Mel-Frequency Cepstral Coefficients
Machine Learning
Artificial Intelligence and Robotics
Computer Sciences
spellingShingle Automatic Speech Classification
Artificial Intelligence
Neural Networks
Mel-Frequency Cepstral Coefficients
Machine Learning
Artificial Intelligence and Robotics
Computer Sciences
Fernandez, Proceso L, Jr
Baquirin, Rey Benjamin M
Artificial Neural Network (ANN) in a Small Dataset to determine Neutrality in the Pronunciation of English as a Foreign Language in Filipino Call Center Agents
description Artificial Neural Networks (ANNs) have continued to be efficient models in solving classification problems. In this paper, we explore the use of an ANN with a small dataset to accurately classify whether Filipino call center agents’ pronunciations are neutral or not based on their employer’s standards. Isolated utterances of the ten most commonly used words in the call center were recorded from eleven agents creating a dataset of 110 utterances. Two learning specialists were consulted to establish ground truths and Cohen’s Kappa was computed as 0.82, validating the reliability of the dataset. The first thirteen Mel-Frequency Cepstral Coefficients (MFCCs) were then extracted from each word and an ANN was trained with Ten-fold Stratified Cross Validation. Experimental results on the model recorded a classification accuracy of 89.60% supported by an overall F-Score of 0.92.
format text
author Fernandez, Proceso L, Jr
Baquirin, Rey Benjamin M
author_facet Fernandez, Proceso L, Jr
Baquirin, Rey Benjamin M
author_sort Fernandez, Proceso L, Jr
title Artificial Neural Network (ANN) in a Small Dataset to determine Neutrality in the Pronunciation of English as a Foreign Language in Filipino Call Center Agents
title_short Artificial Neural Network (ANN) in a Small Dataset to determine Neutrality in the Pronunciation of English as a Foreign Language in Filipino Call Center Agents
title_full Artificial Neural Network (ANN) in a Small Dataset to determine Neutrality in the Pronunciation of English as a Foreign Language in Filipino Call Center Agents
title_fullStr Artificial Neural Network (ANN) in a Small Dataset to determine Neutrality in the Pronunciation of English as a Foreign Language in Filipino Call Center Agents
title_full_unstemmed Artificial Neural Network (ANN) in a Small Dataset to determine Neutrality in the Pronunciation of English as a Foreign Language in Filipino Call Center Agents
title_sort artificial neural network (ann) in a small dataset to determine neutrality in the pronunciation of english as a foreign language in filipino call center agents
publisher Archīum Ateneo
publishDate 2018
url https://archium.ateneo.edu/discs-faculty-pubs/73
https://archium.ateneo.edu/cgi/viewcontent.cgi?article=1072&context=discs-faculty-pubs
_version_ 1681506576469327872