Speaker Recognition Anti-spoofing

Evans, Nicholas; Kinnunen, Tomi; Yamagishi, Junichi; Wu, Zhizheng; Alegre, Federico; León, Phillip L. De

doi:10.1007/978-1-4471-6524-8_7

Cited by 39 publications

(29 citation statements)

References 94 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The EERs of CQCC [7] and CQCC-A [7] are taken from [7]. Earlier work [1][2][3] on spoofing detection showed that phase related features perform better than amplitude-based features. This is because natural phase information is almost entirely lost in spoofed speech realized using voice conversion and speech synthesis approaches [1][2][3].…”

Section: Performance Evaluationmentioning

confidence: 99%

“…Earlier work [1][2][3] on spoofing detection showed that phase related features perform better than amplitude-based features. This is because natural phase information is almost entirely lost in spoofed speech realized using voice conversion and speech synthesis approaches [1][2][3]. It is observed from the results of tables 2 that amplitude-based features (e.g., LFCC, CQCC, and IQCC) can provide better or at least comparable results to that of the phase related features.…”

Section: Performance Evaluationmentioning

confidence: 99%

“…Impersonation, replay, speech synthesis and voice conversion are some examples of spoofing attacks. Impersonation or human mimicking requires a mimic to imitate a target speaker's voice and it does not pose a genuine threat to automatic speaker verification system [1][2][3][4][5]. Replay attacks consist of playing back the pre-recorded voice of a target speaker to spoof the system.…”

Section: Introductionmentioning

confidence: 99%

“…Replay attacks consist of playing back the pre-recorded voice of a target speaker to spoof the system. Liveness detection and detection of channel differences are found to effective in this situation [1,5]. Given the availability of open-source toolkits online, spoofing attacks based on speech synthesis and voice conversion techniques are potentially more serious [1][2][3][4].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Spoofing detection employing infinite impulse response — constant Q transform-based feature representations

Alam

Kenny

2017

2017 25th European Signal Processing Conference (EUSIPCO)

View full text Add to dashboard Cite

Abstract-Speaker recognition researchers acknowledge that systems which aim to verify speakers automatically based on their pronunciation of an utterance are vulnerable to spoofing attacks using voice conversion and speech synthesis technologies. The first automatic speaker verification spoofing and countermeasures challenge (ASVspoof2015) was designed to stimulate interest in this problem among the speaker recognition communities. In the course of the challenge and subsequently, it became clear that the most effective countermeasures against spoofing attacks are low-level acoustic features (typically extracted at 10 ms intervals) designed to detect artifacts in synthetic or voice converted speech. In this work, we demonstrate the effectiveness of the infinite impulse responseconstant Q transform (IIR-CQT) spectrum-based cepstral coefficients (ICQC) as anti-spoofing front-end. The IIR-CQT spectrum is estimated by filtering the multi-resolution fast Fourier transform with an infinite impulse response filter. These features can be used on their own with a standard Gaussian mixture model backend to detect spoofing attacks or they can be used in tandem with bottleneck features which are extracted from a bottleneck layer in a deep neural network designed to discriminate between synthetic and natural speech. We show that the ICQC features are capable of producing very low equal error rates on the individual spoofing attacks in the ASVspoof2015 data set (0.02% on the known attacks, 0.23% on the unknown attacks, and 0.13% on average). Moreover, with a single decision threshold (common to all of the attacks), the ICQC front end yielded an equal error rate of 0.20%.

show abstract

Section: Performance Evaluationmentioning

confidence: 99%

Section: Performance Evaluationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Spoofing detection employing infinite impulse response — constant Q transform-based feature representations

Alam

Kenny

2017

2017 25th European Signal Processing Conference (EUSIPCO)

View full text Add to dashboard Cite

show abstract

“…Impostors may change phonation by using glottal fry or whisper voice; change pitch; change accents by using a foreign accent or another dialect; or do anything else in their power to hide their identities. Especially in forensics, the importance of awareness of voice disguise has been emphasised since the 1970s [1][2][3][4][5][6][7][8][9][10]. In the last two decades, researchers have warned of a new type of voice disguise, the use of synthetic speech [11][12][13].…”

Section: Introductionmentioning

confidence: 99%

Auditory discrimination of natural speech and synthetic speech used as voice disguise

Amino

Makinae

Kamada

2018

Acoust. Sci. & Tech.

View full text Add to dashboard Cite

An assessment of automatic speaker verification vulnerabilities to replay spoofing attacks

Janicki

Alegre

Evans

2016

Security Comm Networks

Self Cite

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

Speaker Recognition Anti-spoofing

Cited by 39 publications

References 94 publications

Spoofing detection employing infinite impulse response — constant Q transform-based feature representations

Spoofing detection employing infinite impulse response — constant Q transform-based feature representations

Auditory discrimination of natural speech and synthetic speech used as voice disguise

An assessment of automatic speaker verification vulnerabilities to replay spoofing attacks

Contact Info

Product

Resources

About