SAS: A speaker verification spoofing database containing diverse attacks

Wu, Zhizheng; Khodabakhsh, Ali; Demiroğlu, Cenk; Yamagishi, Junichi; Saito, Daisuke; Toda, Tomoki; King, Simon

doi:10.1109/icassp.2015.7178810

Cited by 65 publications

(48 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, even the state-of-the-art ASV systems are not designed to sustain spoofing attacks, such as impersonation, replay, speech synthesis and voice conversion, as reviewed in [1]. Specifically, attacks realised by speech synthesis [2] and voice conversion [3], which provide easily accessible ways to generate high quality speech of the target speaker, impose a genuine threat to the ASV systems [4]. To address the threat of these two kinds of synthetic spoofing attacks, one way is to improve the robustness of ASV system by combining the detection process and verification process [5].…”

Section: Introductionmentioning

confidence: 99%

Spoofing detection from a feature representation perspective

Tian

Xiao³

et al. 2016

2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

Spoofing detection, which discriminates the spoofed speech from the natural speech, has gained much attention recently. Lowdimensional features that are used in speaker recognition/verification are also used in spoofing detection. Unfortunately, they don't capture sufficient information required for spoofing detection. In this work, we investigate the use of high-dimensional features for spoofing detection, that maybe more sensitive to the artifacts in the spoofed speech. Six types of high-dimensional feature are employed. For each kind of feature, four different representations are extracted, i.e. the original high-dimensional feature, corresponding low-dimensional feature, the low-and the high-frequency regions of the original high-dimensional feature. Dynamic features are also calculated to assess the effectiveness of the temporal information to detect the artifacts across frames. A neural network-based classifier is adopted to handle the high-dimensional features. Experimental results on the standard ASVspoof 2015 corpus suggest that highdimensional features and dynamic features are useful for spoofing attack detection. A fusion of them has been shown to achieve 0.0% the equal error rates for nine of ten attack types.

show abstract

Section: Introductionmentioning

confidence: 99%

Spoofing detection from a feature representation perspective

Tian

Xiao³

et al. 2016

2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

show abstract

“…They include the series of LivDet evaluations for fingerprint recognition [8] and a similar initiative for face recognition [9]. As of 2014, [6], [7], the first ASVspoof challenge was co-organized in 2015. The initiative lead to the submission of 16 countermeasure systems, all benchmarked and ranked using a common database, protocol, and metric.…”

mentioning

confidence: 99%

“…Stemming from the special session at INTERSPEECH, the creation of a large dataset of genuine and spoofed speech [6], [7] started later in 2013. Following refinements and improvements to the dataset and protocols, the first ASVspoof challenge [11] 1 was organised as a special session at IN-TERSPEECH 2015 held in Dresden, Germany.…”

mentioning

confidence: 99%

ASVspoof: The Automatic Speaker Verification Spoofing and Countermeasures Challenge

Yamagishi

Kinnunen

et al. 2017

IEEE J. Sel. Top. Signal Process.

Self Cite

256

302

View full text Add to dashboard Cite

Abstract-Concerns regarding the vulnerability of automatic speaker verification (ASV) technology against spoofing can undermine confidence in its reliability and form a barrier to exploitation. The absence of competitive evaluations and the lack of common datasets has hampered progress in developing effective spoofing countermeasures. This paper describes the ASV Spoofing and Countermeasures (ASVspoof) initiative, which aims to fill this void. Through the provision of a common dataset, protocols, and metrics, ASVspoof promotes a sound research methodology and fosters technological progress. This paper also describes the ASVspoof 2015 dataset, evaluation, and results with detailed analyses. A review of post-evaluation studies conducted using the same dataset illustrates the rapid progress stemming from ASVspoof and outlines the need for further investigation. Priority future research directions are presented in the scope of the next ASVspoof evaluation planned for 2017.

show abstract

“…Generally speaking, a modern statistical parametric synthesis technique first trains an average voice model from large corpus, which is subsequently adapted to a specific target speaker using a small amount of adaptation utterances [53,51]. Although speech synthesis has been shown to increase the error rates of state-of-the-art systems to unacceptable levels in [31,32,38,8,47], it is not straightforward to perform spoofing, as it requires text input.…”

Section: Related Workmentioning

confidence: 99%

“…However, past work generally focuses on a specific spoofing attacks, and makes the comparison to be difficult. In our previous work [47], speech synthesis and voice conversion attacks have been analysed and compared using the same database in the context of text-independent ASV. In this work, we focus on replay and voice conversion attacks in the context of text-dependent ASV.…”

mentioning

confidence: 99%

On the study of replay and voice conversion attacks to text-dependent speaker verification

2015

Multimed Tools Appl

Self Cite

View full text Add to dashboard Cite

Automatic speaker verification (ASV) is to automatically accept or reject a claimed identity based on a speech sample. Recently, individual studies have confirmed the vulnerability of state-of-the-art text-independent ASV systems under replay, speech synthesis and voice conversion attacks on various databases. However, the behaviours of text-dependent ASV systems have not been systematically assessed in the face of various spoofing attacks. In this work, we first conduct a systematic analysis of text-dependent ASV systems to replay and voice conversion attacks using the same protocol and database, in particular the RSR2015 database which represents mobile device quality speech. We then analyse the interplay of voice conversion and speaker verification by linking the voice conversion objective evaluation measures with the speaker verification error rates to take a look at the vulnerabilities from the perspective of voice conversion.

show abstract

SAS: A speaker verification spoofing database containing diverse attacks

Cited by 65 publications

References 27 publications

Spoofing detection from a feature representation perspective

Spoofing detection from a feature representation perspective

ASVspoof: The Automatic Speaker Verification Spoofing and Countermeasures Challenge

On the study of replay and voice conversion attacks to text-dependent speaker verification

Contact Info

Product

Resources

About