Voice spoofing countermeasure for voice replay attacks using deep learning
In our everyday lives, we communicate with each other using several means and channels of communication, as communication is crucial in the lives of humans. Listening and speaking are the primary forms of communication. For listening and speaking, the human voice is indispensable. Voice communicatio...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier Ltd.
2022
|
Subjects: | |
Online Access: | http://eprints.utm.my/103023/1/DayangNAJawawi2022_VoiceSpoofingCountermeasure.pdf |
_version_ | 1796867379363315712 |
---|---|
author | Zhou, Jincheng Tao, Hai A. Jawawi, Dayang N. Dan, Wang Ibeke, Ebuka Biamba, Cresantus |
author_facet | Zhou, Jincheng Tao, Hai A. Jawawi, Dayang N. Dan, Wang Ibeke, Ebuka Biamba, Cresantus |
author_sort | Zhou, Jincheng |
collection | ePrints |
description | In our everyday lives, we communicate with each other using several means and channels of communication, as communication is crucial in the lives of humans. Listening and speaking are the primary forms of communication. For listening and speaking, the human voice is indispensable. Voice communication is the simplest type of communication. The Automatic Speaker Verification (ASV) system verifies users with their voices. These systems are susceptible to voice spoofing attacks - logical and physical access attacks. Recently, there has been a notable development in the detection of these attacks. Attackers use enhanced gadgets to record users' voices, replay them for the ASV system, and be granted access for harmful purposes. In this work, we propose a secure voice spoofing countermeasure to detect voice replay attacks. We enhanced the ASV system security by building a spoofing countermeasure dependent on the decomposed signals that consist of prominent information. We used two main features- the Gammatone Cepstral Coefficients and Mel-Frequency Cepstral Coefficients- for the audio representation. For the classification of the features, we used Bi-directional Long-Short Term Memory Network in the cloud, a deep learning classifier. We investigated numerous audio features and examined each feature's capability to obtain the most vital details from the audio for it to be labelled genuine or a spoof speech. Furthermore, we use various machine learning algorithms to illustrate the superiority of our system compared to the traditional classifiers. The results of the experiments were classified according to the parameters of accuracy, precision rate, recall, F1-score, and Equal Error Rate (EER). The results were 97%, 100%, 90.19% and 94.84%, and 2.95%, respectively. |
first_indexed | 2024-03-05T21:26:21Z |
format | Article |
id | utm.eprints-103023 |
institution | Universiti Teknologi Malaysia - ePrints |
language | English |
last_indexed | 2024-03-05T21:26:21Z |
publishDate | 2022 |
publisher | Elsevier Ltd. |
record_format | dspace |
spelling | utm.eprints-1030232023-10-12T08:53:36Z http://eprints.utm.my/103023/ Voice spoofing countermeasure for voice replay attacks using deep learning Zhou, Jincheng Tao, Hai A. Jawawi, Dayang N. Dan, Wang Ibeke, Ebuka Biamba, Cresantus QA76 Computer software In our everyday lives, we communicate with each other using several means and channels of communication, as communication is crucial in the lives of humans. Listening and speaking are the primary forms of communication. For listening and speaking, the human voice is indispensable. Voice communication is the simplest type of communication. The Automatic Speaker Verification (ASV) system verifies users with their voices. These systems are susceptible to voice spoofing attacks - logical and physical access attacks. Recently, there has been a notable development in the detection of these attacks. Attackers use enhanced gadgets to record users' voices, replay them for the ASV system, and be granted access for harmful purposes. In this work, we propose a secure voice spoofing countermeasure to detect voice replay attacks. We enhanced the ASV system security by building a spoofing countermeasure dependent on the decomposed signals that consist of prominent information. We used two main features- the Gammatone Cepstral Coefficients and Mel-Frequency Cepstral Coefficients- for the audio representation. For the classification of the features, we used Bi-directional Long-Short Term Memory Network in the cloud, a deep learning classifier. We investigated numerous audio features and examined each feature's capability to obtain the most vital details from the audio for it to be labelled genuine or a spoof speech. Furthermore, we use various machine learning algorithms to illustrate the superiority of our system compared to the traditional classifiers. The results of the experiments were classified according to the parameters of accuracy, precision rate, recall, F1-score, and Equal Error Rate (EER). The results were 97%, 100%, 90.19% and 94.84%, and 2.95%, respectively. Elsevier Ltd. 2022 Article PeerReviewed application/pdf en http://eprints.utm.my/103023/1/DayangNAJawawi2022_VoiceSpoofingCountermeasure.pdf Zhou, Jincheng and Tao, Hai and A. Jawawi, Dayang N. and Dan, Wang and Ibeke, Ebuka and Biamba, Cresantus (2022) Voice spoofing countermeasure for voice replay attacks using deep learning. Journal of Cloud Computing: Advances, Systems and Applications, 11 (51). pp. 1-14. ISSN 2192-113X http://dx.doi.org/10.1186/s13677-022-00306-5 DOI: 10.1186/s13677-022-00306-5 |
spellingShingle | QA76 Computer software Zhou, Jincheng Tao, Hai A. Jawawi, Dayang N. Dan, Wang Ibeke, Ebuka Biamba, Cresantus Voice spoofing countermeasure for voice replay attacks using deep learning |
title | Voice spoofing countermeasure for voice replay attacks using deep learning |
title_full | Voice spoofing countermeasure for voice replay attacks using deep learning |
title_fullStr | Voice spoofing countermeasure for voice replay attacks using deep learning |
title_full_unstemmed | Voice spoofing countermeasure for voice replay attacks using deep learning |
title_short | Voice spoofing countermeasure for voice replay attacks using deep learning |
title_sort | voice spoofing countermeasure for voice replay attacks using deep learning |
topic | QA76 Computer software |
url | http://eprints.utm.my/103023/1/DayangNAJawawi2022_VoiceSpoofingCountermeasure.pdf |
work_keys_str_mv | AT zhoujincheng voicespoofingcountermeasureforvoicereplayattacksusingdeeplearning AT taohai voicespoofingcountermeasureforvoicereplayattacksusingdeeplearning AT ajawawidayangn voicespoofingcountermeasureforvoicereplayattacksusingdeeplearning AT danwang voicespoofingcountermeasureforvoicereplayattacksusingdeeplearning AT ibekeebuka voicespoofingcountermeasureforvoicereplayattacksusingdeeplearning AT biambacresantus voicespoofingcountermeasureforvoicereplayattacksusingdeeplearning |