Jiakang Li

The technique of transforming voices in order to hide the real identity of a speaker is called voice disguise, among which automatic voice disguise (AVD) by modifying the spectral and temporal characteristics of voices with miscellaneous algorithms are easily conducted with softwares accessible to the public. AVD has posed great threat to both human listening and automatic speaker verification (ASV). In this paper, we have found that ASV is not only a victim of AVD but could be a tool to beat some simple types of AVD. Firstly, three types of AVD, pitch scaling, vocal tract length normalization (VTLN) and voice conversion (VC), are introduced as representative methods. State-of-the-art ASV methods are subsequently utilized to objectively evaluate the impact of AVD on ASV by equal error rates (EER). Moreover, an approach to restore disguised voice to its original version is proposed by minimizing a function of ASV scores w.r.t. restoration parameters. Experiments are then conducted on disguised voices from Voxceleb, a dataset recorded in real-world noisy scenario. The results have shown that, for the voice disguise by pitch scaling, the proposed approach obtains an EER around 7% comparing to the 30% EER of a recently proposed baseline using the ratio of fundamental frequencies. The proposed approach generalizes well to restore the disguise with nonlinear frequency warping in VTLN by reducing its EER from 34.3% to 18.5%. However, it is difficult to restore the source speakers in VC by our approach, where more complex forms of restoration functions or other paralinguistic cues might be necessary to restore the nonlinear transform in VC. Finally, contrastive visualization on ASV features with and without restoration illustrate the role of the proposed approach in an intuitive way.

Automatic speaker verification (ASV) is an emerging biometric verification technique with more and more applications. However, both verification accuracy and anti-spoofing should be considered carefully before putting ASV into practice, where anti-spoofing is also called replay detection in which voice is recorded, stored and replayed to deceive ASV systems. Cascaded decision of anti-spoofing and ASV is a straightforward solution to tackle the two issues. In this paper, joint decision of anti-spoofing and ASV was investigated in a multi-task learning framework with contrastive loss in order to improve the cascaded decision approach. A modified triplet loss was firstly constructed to supervise deep neural networks to extract embedding vectors containing information of both speaker identity and spoofing. The embedding vectors were subsequently taken as input features by back-end classifiers towards speaker and spoofing classification. The experimental results on both ASVspoof 2017 and ASVspoof 2019 showed that the proposed joint decision approach with triplet loss outperformed the corresponding baselines, a recent work on joint decision with Gaussian back-end fusion and our previous joint decision approach with cross-entropy loss.

Even though audio replay detection has improved in recent years, its performance is known to severely deteriorate with the existence of strong background noises. Given the fact that different frames of an utterance have different impacts on the performance of spoofing detection, this paper introduces attention-based long short-term memory (LSTM) to extract representative frames for spoofing detection in noisy environments. With this attention mechanism, the specific and representative frame-level features will be automatically selected by adjusting their weights in the framework of attention-based LSTM. The experiments, conducted using the ASVspoof 2017 dataset version 2.0, show that the equal error rate (EER) of the proposed approach was about 13% lower than the constant Q cepstral coefficients-Gaussian mixture model (CQCC-GMM) baseline in noisy environments with four different signal-to-noise ratios (SNR). Meanwhile, the proposed algorithm also improved the performance of traditional LSTM on audio replay detection systems in noisy environments. Experiments using bagging with different frame lengths were also conducted to further improve the proposed approach.