Uncertainty assessment for detection of spoofing attacks to speaker verification systems using a Bayesian approach

Süslü, Çağıl; Eren, Eray; Demiroğlu, Cenk

doi:10.1016/j.specom.2021.12.003

Cited by 3 publications

(1 citation statement)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the weaknesses of the CNN is its uncertainty, which may occur due to the use of the softmax layer in the CNN. A Bayesian approach was proposed in Reference [ 69 ], which strengthened the assessment of uncertainty in CNN. However, their EER was quite high for a development dataset.…”

Section: Experimentation and Analysismentioning

confidence: 99%

Gaussian-Filtered High-Frequency-Feature Trained Optimized BiLSTM Network for Spoofed-Speech Classification

Mewada,

Al-Asad,

Almalki

et al. 2023

Sensors

View full text Add to dashboard Cite

Voice-controlled devices are in demand due to their hands-free controls. However, using voice-controlled devices in sensitive scenarios like smartphone applications and financial transactions requires protection against fraudulent attacks referred to as “speech spoofing”. The algorithms used in spoof attacks are practically unknown; hence, further analysis and development of spoof-detection models for improving spoof classification are required. A study of the spoofed-speech spectrum suggests that high-frequency features are able to discriminate genuine speech from spoofed speech well. Typically, linear or triangular filter banks are used to obtain high-frequency features. However, a Gaussian filter can extract more global information than a triangular filter. In addition, MFCC features are preferable among other speech features because of their lower covariance. Therefore, in this study, the use of a Gaussian filter is proposed for the extraction of inverted MFCC (iMFCC) features, providing high-frequency features. Complementary features are integrated with iMFCC to strengthen the features that aid in the discrimination of spoof speech. Deep learning has been proven to be efficient in classification applications, but the selection of its hyper-parameters and architecture is crucial and directly affects performance. Therefore, a Bayesian algorithm is used to optimize the BiLSTM network. Thus, in this study, we build a high-frequency-based optimized BiLSTM network to classify the spoofed-speech signal, and we present an extensive investigation using the ASVSpoof 2017 dataset. The optimized BiLSTM model is successfully trained with the least epoch and achieved a 99.58% validation accuracy. The proposed algorithm achieved a 6.58% EER on the evaluation dataset, with a relative improvement of 78% on a baseline spoof-identification system.

show abstract

Section: Experimentation and Analysismentioning

confidence: 99%

Gaussian-Filtered High-Frequency-Feature Trained Optimized BiLSTM Network for Spoofed-Speech Classification

Mewada,

Al-Asad,

Almalki

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

Detecting Replay Attack on Voice-Controlled Systems using Small Neural Networks

Ahmed

Khan

Sheta

et al. 2022

2022 IEEE 7th Forum on Research and Technologies for Society and Industry Innovation (RTSI)

View full text Add to dashboard Cite

Generalized Replay Spoofing Countermeasure Based on Combining Local Subclassification Models

2022

View full text Add to dashboard Cite

Automatic speaker verification (ASV) systems play a prominent role in the security field due to the usability of voice biometrics compared to alternative biometric authentication modalities. Nevertheless, ASV systems are susceptible to malicious voice spoofing attacks. In response to such threats, countermeasures have been devised to prevent breaches and ensure the safety of user data by categorizing utterances as either genuine or spoofed. In this paper, we propose a new voice spoofing countermeasure that seeks to improve the generalization of supervised learning models. This is accomplished by alleviating the problem of intraclass variance. Specifically, the proposed approach addresses the generalization challenge by splitting the classification problem into a set of local subproblems in order to lessen the supervised learning task. The system outperformed existing state-of-the-art approaches with an EER of 0.097% on the ASVspoof challenge corpora related to replaying spoofing attacks.

show abstract

Uncertainty assessment for detection of spoofing attacks to speaker verification systems using a Bayesian approach

Cited by 3 publications

References 31 publications

Gaussian-Filtered High-Frequency-Feature Trained Optimized BiLSTM Network for Spoofed-Speech Classification

Gaussian-Filtered High-Frequency-Feature Trained Optimized BiLSTM Network for Spoofed-Speech Classification

Detecting Replay Attack on Voice-Controlled Systems using Small Neural Networks

Generalized Replay Spoofing Countermeasure Based on Combining Local Subclassification Models

Contact Info

Product

Resources

About