Some Results from the Biosecure Talking Face Evaluation Campaign

Fauve, Benoit; Bredin, Hervé; Karam, Walid; Verdet, Florian; Mayoue, Aurélien; Chollet, G.; Hennebert, Jean; Lewis, Richard P.; Mason, John S.; Mokbel, Chafic; Petrovska, D.

doi:10.1109/icassp.2008.4518565

Cited by 11 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It fits a three‐component GMM to the log‐energy distribution and adjusts the speech/non‐speech threshold according to the GMM parameters . This approach has been used successfully in many independent studies, for example, .…”

Section: Methodsmentioning

confidence: 99%

An assessment of automatic speaker verification vulnerabilities to replay spoofing attacks

Janicki

Alegre

Evans

2016

Security Comm Networks

View full text Add to dashboard Cite

This paper analyses the threat of replay spoofing or presentation attacks in the context of automatic speaker verification. As relatively high‐technology attacks, speech synthesis and voice conversion, which have thus far received far greater attention in the literature, are probably beyond the means of the average fraudster. The implementation of replay attacks, in contrast, requires no specific expertise nor sophisticated equipment. Replay attacks are thus likely to be the most prolific in practice, while their impact is relatively under‐researched. The work presented here aims to compare at a high level the threat of replay attacks with those of speech synthesis and voice conversion. The comparison is performed using strictly controlled protocols and with six different automatic speaker verification systems including a state‐of‐the‐art iVector/probabilistic linear discriminant analysis system. Experiments show that low‐effort replay attacks present at least a comparable threat to speech synthesis and voice conversion. The paper also describes and assesses two replay attack countermeasures. A relatively new approach based on the local binary pattern analysis of speech spectrograms is shown to outperform a competing approach based on the detection of far‐field recordings. Copyright © 2016 John Wiley & Sons, Ltd.

show abstract

Section: Methodsmentioning

confidence: 99%

An assessment of automatic speaker verification vulnerabilities to replay spoofing attacks

Janicki

Alegre

Evans

2016

Security Comm Networks

View full text Add to dashboard Cite

show abstract

“…Most researches focus on the 2D spoofing attack [5][6][7][8][9][10][11][12][13][14][15][16][17][18].…”

Section: Related Workmentioning

confidence: 99%

“…Thus, the development of the face liveness detection system is necessary to improve the security of the system. The existing counter systems for 2D spoofing attacks can be classified in two categories: the user-cooperative systems [5][6][7][8][9] and the non-user-cooperative systems [10][11][12][13][14][15][16][17][18]. The user-cooperative systems require users to do specific tasks, e.g.…”

Section: Introductionmentioning

confidence: 99%

Face liveness detection using analysis of Fourier spectra based on hair

Liu

2014

2014 International Conference on Wavelet Analysis and Pattern Recognition

View full text Add to dashboard Cite

The existing face liveness detection algorithms have satisfying performance on spoofing photos by detecting the biological motion, including eye blinking, head rotation and mouth movement. However, the biological motions can be simulated by using video, which is called a video playback attack. This paper proposes a countermeasure to a video playback attack by analyzing the detail of hair using the Fourier spectra. We apply a flashlight to enhance the difference between the real person and the video playback attack. Experimental results suggest that the proposed method has an encouraging performance on face liveness detection.

show abstract

“…The speaker verification systems submitted by Swansea University and Validsoft are based on standard Gaussian Mixture Models (GMMs) [51], whose originality lies in the use of wide band feature extractors, an idea already explored by Swansea University during the Biosecure evaluation campaign [26]. They were developed using SPro 3 and ALIZE [9] open source toolkits.…”

Section: Swansea University and Validsoft (Suv)mentioning

confidence: 99%

On the Results of the First Mobile Biometry (MOBIO) Face and Speaker Verification Evaluation

Marcel

McCool

Matějka

et al. 2010

Recognizing Patterns in Signals, Speech, Images and Videos

Self Cite

View full text Add to dashboard Cite

International audienceThis paper evaluates the performance of face and speaker verification techniques in the context of a mobile environment. The mobile environment was chosen as it provides a realistic and challenging test-bed for biometric person verification techniques to operate. For instance the audio environment is quite noisy and there is limited control over the illumination conditions and the pose of the subject for the video. To conduct this evaluation, a part of a database captured during the " Mobile Biometry " (MOBIO) European Project was used. In total there were nine participants to the evaluation who submitted a face verification system and five participants who submitted speaker verification systems. The results have shown that the best performing face and speaker verification systems obtained the same level of performance, respectively 10.9% and 10.6% of HTER

show abstract

Some Results from the Biosecure Talking Face Evaluation Campaign

Cited by 11 publications

References 8 publications

An assessment of automatic speaker verification vulnerabilities to replay spoofing attacks

An assessment of automatic speaker verification vulnerabilities to replay spoofing attacks

Face liveness detection using analysis of Fourier spectra based on hair

On the Results of the First Mobile Biometry (MOBIO) Face and Speaker Verification Evaluation

Contact Info

Product

Resources

About