Spoofing Speech Detection Using Modified Relative Phase Information

Wang, Longbiao; Nakagawa, Seiichi; Zhang, Zhaofeng; Yoshida, Yohei; Kawakami, Yuta

doi:10.1109/jstsp.2017.2694139

Cited by 41 publications

(20 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Phase-based features have shown effective for synthesized and converted speech detection [12,18,19,20]. The most commonly used phase related feature may be the group delay based feature.…”

Section: Introductionmentioning

confidence: 99%

Multiple Phase Information Combination for Replay Attacks Detection

Wang

Dang

et al. 2018

Interspeech 2018

Self Cite

View full text Add to dashboard Cite

In recent years, the performance of Automatic Speaker Verification (ASV) systems has been improved significantly. However, they are still affected by different kind of spoofing attacks. In this paper, we propose a method that fused different phase features and amplitude features to detect replay attacks. We apply the mel-scale relative phase feature and source-filter vocal tract feature in phase domain for replay attacks detection. These two phase-based features are combined to get complementary information. In addition to these phase characteristics, constant Q cepstral coefficients (CQCCs) are used. The proposed methods are evaluated using the ASVspoof 2017 challenge database, and Gaussian mixture model was used as the back-end model. The proposed approach achieved 55.6% relative error reduction rate than the conventional magnitude-based feature.

show abstract

“…Phase-based features have shown effective for synthesized and converted speech detection [12,18,19,20]. The most commonly used phase related feature may be the group delay based feature.…”

Section: Introductionmentioning

confidence: 99%

Multiple Phase Information Combination for Replay Attacks Detection

Wang

Dang

et al. 2018

Interspeech 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…e ordinary frequency is converted to Mel frequency, and the first 12 steps of MFCC are extracted. e most widely used classifiers for speech recognition are HMM [25,26], GMM [27,28], ANN [29,30], and SVM [31,32]. In this paper, to improve the separability of data, the SVM classifier is used to generate a nonlinear mapping of the original features to a high-dimensional space; the choice of kernel function is Radial Basis Function (RBF).…”

Section: Mfcc Feature Extractionmentioning

confidence: 99%

Nonlinear Dynamic Feature Extraction Based on Phase Space Reconstruction for the Classification of Speech and Emotion

Sun

Zhang

Song

et al. 2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Due to the shortcomings of linear feature parameters in speech signals, and the limitations of existing time- and frequency-domain attribute features in characterizing the integrity of the speech information, in this paper, we propose a nonlinear method for feature extraction based on the phase space reconstruction (PSR) theory. First, the speech signal was analyzed using a nonlinear dynamic model. Then, the model was used to reconstruct a one-dimensional time speech signal. Finally, nonlinear dynamic (NLD) features based on the reconstruction of the phase space were extracted as the new characteristic parameters. Then, the performance of NLD features was verified by comparing their recognition rates with those of other features (NLD features, prosodic features, and MFCC features). Finally, the Korean isolated words database, the Berlin emotional speech database, and the CASIA emotional speech database were chosen for validation. The effectiveness of the NLD features was tested using the Support Vector Machine classifier. The results show that NLD features not only have high recognition rate and excellent antinoise performance for speech recognition tasks but also can fully characterize the different emotions contained in speech signals.

show abstract

“…The steps involved in extracting MGDCC features are shown in fig 5 [5]. Group delay from the Fourier transform is obtained by calculating the derivative of phase and negating the resultant.…”

Section: Fig 5 Block Representation Of Mgdcc Extractionmentioning

confidence: 99%

“…Previous work on spoofing detection using group delay states that group delay with some modification is better than initially obtained group delay [5]. The extraction of cepstral coefficients from the modified group delay function, DCT is applied as follows Where M is the order of DCT and g(m) is the group delay function.…”

Section: Fig 5 Block Representation Of Mgdcc Extractionmentioning

confidence: 99%

Spoofing Detection and Countermeasure in Automatic Speaker Verification System using Dynamic Features

Neelima¹,

Prabha²

2020

IJRTE

View full text Add to dashboard Cite

This present paper aims to extract robust dynamic features used to spoofing detection and countermeasure in ASV system. ASV is a biometric person authentication system. Researchers are aiming to develop spoofing detection and countermeasure techniques to protect this system against different spoofing attacks. For this, replayed attack is considered, because of very common accessibility of recording devices. In replay spoofing, the speech utterances of target (genuine) speakers are recorded and played against ASV system for gaining access unauthorizedly. For this purpose, as a first step, different dynamic features will be extracted for each speech sample. For feature extraction MFCC, LFCC, and MGDCC feature extraction techniques are used. As a second step, a classifier is used to classify whether the given speech sample is genuine or not. As a classifier, GMM and universal background model is used. In this present work, GMM based ASV system and Countermeasure systems using different feature extraction techniques are developed, and the performance of the methods is evaluated using EER and t- DCF. Basing on the performance values, the best feature extraction technique is selected.

show abstract

Spoofing Speech Detection Using Modified Relative Phase Information

Cited by 41 publications

References 32 publications

Multiple Phase Information Combination for Replay Attacks Detection

Multiple Phase Information Combination for Replay Attacks Detection

Nonlinear Dynamic Feature Extraction Based on Phase Space Reconstruction for the Classification of Speech and Emotion

Spoofing Detection and Countermeasure in Automatic Speaker Verification System using Dynamic Features

Contact Info

Product

Resources

About