Evaluation of Speaker Verification Security and Detection of HMM-Based Synthetic Speech

León, Phillip L. De; Pucher, Michael; Yamagishi, Junichi; Hernáez, Inmaculada; Saratxaga, Ibon

doi:10.1109/tasl.2012.2201472

Cited by 211 publications

(118 citation statements)

References 40 publications

Supporting

Mentioning

111

Contrasting

Unclassified

Order By: Relevance

“…These methods use features mostly based on the audio spectrogram, such as spectral-and cepstralbased features [17], phase-based features [18], the combination of amplitude and phase features [19], and audio quality based features [20]. Features directly extracted from a spectrogram can also be used, as per the recent work that relies on local maxima of spectrogram [21], which showed an impressive performance, albeit for the evaluation database that was based on a set of speech recordings collected with VoIP phones, which provided little challenge for an anti-spoofing system.…”

Section: A Featuresmentioning

confidence: 99%

Impact of Score Fusion on Voice Biometrics and Presentation Attack Detection in Cross-Database Evaluations

Korshunov

Marcel

2017

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

Abstract-Research in the area of automatic speaker verification (ASV) has advanced enough for the industry to start using ASV systems in practical applications. However, these systems are highly vulnerable to spoofing or presentation attacks, limiting their wide deployment. Therefore, it is important to develop mechanisms that can detect such attacks, and it is equally important for these mechanisms to be seamlessly integrated into existing ASV systems for practical and attack-resistant solutions. To be practical, however, an attack detection should have (i) high accuracy, (ii) be well-generalized for different attacks, and (iii) be simple and efficient. Several audio-based presentation attack detection (PAD) methods have been proposed recently but their evaluation was usually done on a single, often obscure, database with limited number of attacks. Therefore, in this paper, we conduct an extensive study of eight state of the art PAD methods and evaluate their ability to detect known and unknown attacks (e.g., in a cross-database scenario) using two major publicly available speaker databases with spoofing attacks: AVspoof and ASVspoof. We investigate whether combining several PAD systems via score fusion can improve attack detection accuracy. We also study the impact of fusing PAD systems (via parallel and cascading schemes) with two i-vector and inter-session variability (ISV)-based ASV systems on the overall performance in both bona fide (no attacks) and spoof scenarios. The evaluation results question the efficiency and practicality of the existing PAD systems, especially when comparing results for individual databases and cross-database data. Fusing several PAD systems can lead to a slightly improved performance, however, how to select which systems to fuse remains an open question. Joint ASV-PAD systems show a significantly increased resistance to the attacks at the expense of slightly degraded performance for bona fide scenarios.

show abstract

Section: A Featuresmentioning

confidence: 99%

Impact of Score Fusion on Voice Biometrics and Presentation Attack Detection in Cross-Database Evaluations

Korshunov

Marcel

2017

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

show abstract

“…Existing approaches to feature extraction for speech spoofing attack detection methods include spectral-and cepstral-based features [8], phase-based features [9], the combination of amplitude and phase features of the spectrogram [17], and audio quality based features [18]. Features directly extracted from a spectrogram can also be used, as per the recent work that relies on local maxima of spectrogram [19].…”

Section: Featuresmentioning

confidence: 99%

“…Compared to cepstral coefficients, using phase information extracted from the signal seem to be more effective for anti-spoofing detection, as it was shown by De Leon et al [9] and Wu et al [20]. However, the most popular recent approaches rely on the combination of spectral-based and phase-based features [17,21,22,23].…”

Section: Featuresmentioning

confidence: 99%

See 1 more Smart Citation

Presentation attack detection in voice biometrics

Korshunov¹,

Marcel²

2017

User-Centric Privacy and Security in Biometrics

View full text Add to dashboard Cite

Recent years have shown an increase in both the accuracy of biometric systems and their practical use. The application of biometrics is becoming widespread with fingerprint sensors in smartphones, automatic face recognition in social networks and video-based applications, and speaker recognition in phone banking and other phone-based services. The popularization of the biometric systems, however, exposed their major flaw -high vulnerability to spoofing attacks [1]. A fingerprint sensor can be easily tricked with a simple glue-made mold, a face recognition system can be accessed using a printed photo, and a speaker recognition system can be spoofed with a replay of pre-recorded voice. The ease with which a biometric system can be spoofed demonstrates the importance of developing efficient anti-spoofing systems that can detect both known (conceivable now) and unknown (possible in the future) spoofing attacks.Therefore, it is important to develop mechanisms that can detect such attacks, and it is equally important for these mechanisms to be seamlessly integrated into existing biometric systems for practical and attack-resistant solutions. To be practical, however, an attack detection should have (i) high accuracy, (ii) be well-generalized for different attacks, and (iii) be simple and efficient.One reason for the increasing demand for effective presentation attack detection (PAD) systems is the ease of access to people's biometric data. So often, a potential attacker can almost effortlessly obtain necessary biometric samples from social networks, including facial images, audio and video recordings, and even extract fingerprints from high resolution images. Therefore, various privacy protection solutions, such as legal privacy requirements and algorithms for obfuscating personal information, e.g., visual privacy filters [2], as well as, social awareness of threats to privacy can also increase security of personal information and potentially reduce the vulnerability of biometric systems.In this chapter, however, we focus on presentation attacks detection in voice biometrics, i.e., automatic speaker verification (ASV) systems. We discuss vulnerabilities of these systems to presentation attacks (PAs), present different state of the art 1

show abstract

“…Relative Phase Shift (RPS) representation (Saratxaga et al, 2009) for the harmonic phase has also be used to build SSD systems aimed to detect spoofing signals created with adapted synthetic voices (De Leon et al, 2011) (De Leon et al, 2012 with good results. The initial works were focused on evaluating the actual capability of the RPSs to detect the phase modifications due to the synthetic generation of the spoofing signals.…”

Section: Introductionmentioning

confidence: 99%

Synthetic speech detection using phase information

Saratxaga

Sánchez

et al. 2016

Speech Communication

Self Cite

View full text Add to dashboard Cite

Taking advantage of the fact that most of the speech processing techniques neglect the phase information, we seek to detect phase perturbations in order to prevent synthetic impostors attacking Speaker Verification systems. Two Synthetic Speech Detection (SSD) systems that use spectral phase related information are reviewed and evaluated in this work: one based on the Modified Group Delay (MGD), and the other based on the Relative Phase Shift, (RPS). A classical modulebased MFCC system is also used as baseline. Different training strategies are proposed and evaluated using both real spoofing samples and copy-synthesized signals from the natural ones, aiming to alleviate the issue of getting real data to train the systems. The recently published ASVSpoof2015 database is used for training and evaluation. Performance with completely unrelated data is also checked using synthetic speech from the Blizzard Challenge as evaluation material. The results prove that phase information can be successfully used for the SSD task even with unknown attacks.

show abstract

Evaluation of Speaker Verification Security and Detection of HMM-Based Synthetic Speech

Cited by 211 publications

References 40 publications

Impact of Score Fusion on Voice Biometrics and Presentation Attack Detection in Cross-Database Evaluations

Impact of Score Fusion on Voice Biometrics and Presentation Attack Detection in Cross-Database Evaluations

Presentation attack detection in voice biometrics

Synthetic speech detection using phase information

Contact Info

Product

Resources

About