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.

An increasing number of independent studies have confirmed the vulnerability of automatic speaker verification (ASV) technology to spoofing. However, in comparison to that involving other biometric modalities, spoofing and countermeasure research for ASV is still in its infancy. A current barrier to progress is the lack of standards which impedes the comparison of results generated by different researchers. The ASVspoof initiative aims to overcome this bottleneck through the provision of standard corpora, protocols and metrics to support a common evaluation. This paper introduces the first edition, summaries the results and discusses directions for future challenges and research.

Abstract. Probabilistic linear discriminant analysis (PLDA) is commonly used in biometric authentication. We review three PLDA variants -standard, simplified and two-covariance -and show how they are related. These clarifications are important because the variants were introduced in literature without argumenting their benefits. We analyse their predictive power, covariance structure and provide scalable algorithms for straightforward implementation of all the three variants. Experiments involve state-of-the-art speaker verification with i-vector features.

Automatic speaker verification (ASV) technology is recently finding its way to end-user applications for secure access to personal data, smart services or physical facilities. Similar to other biometric technologies, speaker verification is vulnerable to spoofing attacks where an attacker masquerades as a particular target speaker via impersonation, replay, text-to-speech (TTS) or voice conversion (VC) techniques to gain illegitimate access to the system. We focus on TTS and VC that represent the most flexible, high-end spoofing attacks. Most of the prior studies on synthesized or converted speech detection report their findings using high-quality clean recordings. Meanwhile, the performance of spoofing detectors in the presence of additive noise, an important consideration in practical ASV implementations, remains largely unknown. To this end, our study provides a comparative analysis of existing state-of-the-art, off-the-shelf synthetic speech detectors under additive noise contamination with a special focus on front-end processing that has been found critical. Our comparison includes eight acoustic feature sets, five related to spectral magnitude and three to spectral phase information. All the methods contain a number of internal control parameters. Except for feature post-processing steps (deltas and cepstral mean normalization) that we optimized for each method, we fix the internal control parameters to their default values based on literature, and compare all the variants using the exact same dimensionality and back-end system. In addition to the eight feature sets, we consider two alternative classifier back-ends: Gaussian mixture model (GMM) and i-vector, the latter with both cosine scoring and probabilistic linear discriminant analysis (PLDA) scoring. Our extensive analysis on the recent ASVspoof 2015 challenge provides new insights to the robustness of the spoofing detectors. Firstly, unlike in most other speech processing tasks, all the compared spoofing detectors break down even at relatively high signal-to-noise ratios (SNRs) and fail to generalize to noisy conditions even if performing excellently on clean data. This indicates both difficulty of the task, as well as potential to over-fit the methods easily. Secondly, speech enhancement pre-processing is not found helpful. Thirdly, GMM back-end generally outperforms the more involved i-vector back-end. Fourthly, concerning the compared features, the Mel-frequency cepstral coefficient (MFCC) and subband spectral centroid magnitude coefficient (SCMC) features perform the best on average though the winner method depends on SNR and noise type. Finally, a study with two score fusion strategies shows that combining different feature based systems improves recognition accuracy for known and unknown attacks in both clean and noisy conditions. In particular, simple score averaging fusion, as opposed to weighted fusion with logistic loss weight optimization, was found to work better, on average. For clean speech, it provides 88% and 28% relative improvements ...

Automatic speaker verification (ASV) systems are highly vulnerable against spoofing attacks, also known as imposture. With recent developments in speech synthesis and voice conversion technology, it has become important to detect synthesized or voice-converted speech for the security of ASV systems. In this paper, we compare five different classifiers used in speaker recognition to detect synthetic speech. Experimental results conducted on the ASVspoof 2015 dataset show that support vector machines with generalized linear discriminant kernel (GLDS-SVM) yield the best performance on the development set with the EER of 0.12 % whereas Gaussian mixture model (GMM) trained using maximum likelihood (ML) criterion with the EER of 3.01 % is superior for the evaluation set.

Any biometric recognizer is vulnerable to direct spoofing attacks and automatic speaker verification (ASV) is no exception; replay, synthesis and conversion attacks all provoke false acceptances unless countermeasures are used. We focus on voice conversion (VC) attacks. Most existing countermeasures use full knowledge of a particular VC system to detect spoofing. We study a potentially more universal approach involving generative modeling perspective. Specifically, we adopt standard ivector representation and probabilistic linear discriminant analysis (PLDA) back-end for joint operation of spoofing attack detector and ASV system. As a proof of concept, we study a vocoder-mismatched ASV and VC attack detection approach on the NIST 2006 speaker recognition evaluation corpus. We report stand-alone accuracy of both the ASV and countermeasure systems as well as their combination using score fusion and joint approach. The method holds promise.

Abstract-Any biometric recognizer is vulnerable to spoofing attacks and hence voice biometric, also called automatic speaker verification (ASV), is no exception; replay, synthesis and conversion attacks all provoke false acceptances unless countermeasures are used. We focus on voice conversion (VC) attacks considered as one of the most challenging for modern recognition systems. To detect spoofing, most existing countermeasures assume explicit or implicit knowledge of a particular VC system and focus on designing discriminative features. In this work, we explore backend generative models for more generalized countermeasures. Specifically, we model synthesis-channel subspace to perform speaker verification and anti-spoofing jointly in the i-vector space, which is a well-established technique for speaker modeling. It enables us to integrate speaker verification and anti-spoofing tasks into one system without any fusion techniques. To validate the proposed approach, we study vocoder-matched and vocodermismatched ASV and VC spoofing detection on the NIST 2006 speaker recognition evaluation dataset. Promising results are obtained for standalone countermeasures as well as their combination with ASV systems using score fusion and joint approach.

The series of language recognition evaluations (LRE's) conducted by the National Institute of Standards and Technology (NIST) have been one of the driving forces in advancing spoken language recognition technology. This paper presents a shared view of five institutions resulting from our collaboration toward LRE 2015 submissions under the names of I2R, Fan-tastic4, and SingaMS. Among others, LRE'15 emphasizes on language detection in the context of closely related languages, which is different from previous LRE's. From the perspective of language recognition system design, we have witnessed a major paradigm shift in adopting deep neural network (DNN) for both feature extraction and classifier. In particular, deep bottleneck features (DBF) have a significant advantage in replacing the shifted-delta-cepstral (SDC) which has been the only option in the past. We foresee deep learning is going to serve as a major driving force in advancing spoken language recognition system in the coming years. Index Terms: spoken language recognition, evaluation 2. Baseline, data and performance metric 2.1. BaselineWe started off with the baseline system as shown in Fig. 1. Speech utterances are first parameterized as sequences of shifted delta cepstral (SDC) feature vectors [7,8]. They are then represented as i-vectors which compress the variable-length sequences along the time axis and project the resulting vectors to the low-dimensional total variability space. Having its root in