Artificial speech detection using image-based features and random forest classifier
The ASV spoof 2015 Challenge was one of the efforts of the research community in the field of speech processing to foster the development of generalized countermeasures against spoofing attacks. However, most countermeasures submitted to the ASV spoof 2015 Challenge failed to detect the S10 attack e...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English English |
Published: |
Intelektual Pustaka Media Utama (IPMU)
2022
|
Subjects: | |
Online Access: | https://eprints.ums.edu.my/id/eprint/32707/1/Artificial%20speech%20detection%20using%20image.pdf https://eprints.ums.edu.my/id/eprint/32707/2/Artificial%20speech%20detection%20using%20image1.pdf https://eprints.ums.edu.my/id/eprint/32707/ https://ijai.iaescore.com/index.php/IJAI/article/view/21201 http://doi.org/10.11591/ijai.v11.i1.pp161-172 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.ums.eprints.32707 |
---|---|
record_format |
eprints |
spelling |
my.ums.eprints.327072022-06-09T00:41:07Z https://eprints.ums.edu.my/id/eprint/32707/ Artificial speech detection using image-based features and random forest classifier Tan, Choon Beng Mohd Hanafi Ahmad Hijazi Frazier Kok Mohd Saberi Mohamad Puteri Nor Ellyza Nohuddin QA75.5-76.95 Electronic computers. Computer science The ASV spoof 2015 Challenge was one of the efforts of the research community in the field of speech processing to foster the development of generalized countermeasures against spoofing attacks. However, most countermeasures submitted to the ASV spoof 2015 Challenge failed to detect the S10 attack effectively, the only attack that was generated using the waveform concatenation approach. Hence, more informative features are needed to detect previously unseen spoofing attacks. This paper presents an approach that uses data transformation techniques to engineer image-based features together with random forest classifier to detect artificial speech. The objectives are two-fold: (i) to extract image-based features from the Mel frequency cepstral coefficients representation of the speech signal and (ii) to compare the performance of using the extracted features and Random Forest to determine the authenticity of voices with the existing approaches. An audio-to-image transformation technique was used to engineer new features in classifying genuine and spoof voices. An experiment was conducted to find the appropriate combination of the engineered features and classifier. Experimental results showed that the proposed approach was able to detect speech synthesis and voice conversion attacks effectively, with an equal error rate of 0.10% and accuracy of 99.93%. Intelektual Pustaka Media Utama (IPMU) 2022 Article PeerReviewed text en https://eprints.ums.edu.my/id/eprint/32707/1/Artificial%20speech%20detection%20using%20image.pdf text en https://eprints.ums.edu.my/id/eprint/32707/2/Artificial%20speech%20detection%20using%20image1.pdf Tan, Choon Beng and Mohd Hanafi Ahmad Hijazi and Frazier Kok and Mohd Saberi Mohamad and Puteri Nor Ellyza Nohuddin (2022) Artificial speech detection using image-based features and random forest classifier. IAES International Journal of Artificial Intelligence (IJ-AI), 11 (1). pp. 161-172. ISSN 2252-8938 https://ijai.iaescore.com/index.php/IJAI/article/view/21201 http://doi.org/10.11591/ijai.v11.i1.pp161-172 |
institution |
Universiti Malaysia Sabah |
building |
UMS Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Malaysia Sabah |
content_source |
UMS Institutional Repository |
url_provider |
http://eprints.ums.edu.my/ |
language |
English English |
topic |
QA75.5-76.95 Electronic computers. Computer science |
spellingShingle |
QA75.5-76.95 Electronic computers. Computer science Tan, Choon Beng Mohd Hanafi Ahmad Hijazi Frazier Kok Mohd Saberi Mohamad Puteri Nor Ellyza Nohuddin Artificial speech detection using image-based features and random forest classifier |
description |
The ASV spoof 2015 Challenge was one of the efforts of the research community in the field of speech processing to foster the development of generalized countermeasures against spoofing attacks. However, most countermeasures submitted to the ASV spoof 2015 Challenge failed to detect the S10 attack effectively, the only attack that was generated using the waveform concatenation approach. Hence, more informative features are needed to detect previously unseen spoofing attacks. This paper presents an approach that uses data transformation techniques to engineer image-based features together with random forest classifier to detect artificial speech. The objectives are two-fold: (i) to extract image-based features from the Mel frequency cepstral coefficients representation of the speech signal and (ii) to compare the performance of using the extracted features and Random Forest to determine the authenticity of voices with the existing approaches. An audio-to-image transformation technique was used to engineer new features in classifying genuine and spoof voices. An experiment was conducted to find the appropriate combination of the engineered features and classifier. Experimental results showed that the proposed approach was able to detect speech synthesis and voice conversion attacks effectively, with an equal error rate of 0.10% and accuracy of 99.93%. |
format |
Article |
author |
Tan, Choon Beng Mohd Hanafi Ahmad Hijazi Frazier Kok Mohd Saberi Mohamad Puteri Nor Ellyza Nohuddin |
author_facet |
Tan, Choon Beng Mohd Hanafi Ahmad Hijazi Frazier Kok Mohd Saberi Mohamad Puteri Nor Ellyza Nohuddin |
author_sort |
Tan, Choon Beng |
title |
Artificial speech detection using image-based features and random forest classifier |
title_short |
Artificial speech detection using image-based features and random forest classifier |
title_full |
Artificial speech detection using image-based features and random forest classifier |
title_fullStr |
Artificial speech detection using image-based features and random forest classifier |
title_full_unstemmed |
Artificial speech detection using image-based features and random forest classifier |
title_sort |
artificial speech detection using image-based features and random forest classifier |
publisher |
Intelektual Pustaka Media Utama (IPMU) |
publishDate |
2022 |
url |
https://eprints.ums.edu.my/id/eprint/32707/1/Artificial%20speech%20detection%20using%20image.pdf https://eprints.ums.edu.my/id/eprint/32707/2/Artificial%20speech%20detection%20using%20image1.pdf https://eprints.ums.edu.my/id/eprint/32707/ https://ijai.iaescore.com/index.php/IJAI/article/view/21201 http://doi.org/10.11591/ijai.v11.i1.pp161-172 |
_version_ |
1760231063188144128 |
score |
13.18916 |