Proceedings ArticleDOI
Spoofing-Aware Speaker Verification with Unsupervised Domain Adaptation
Xuechen Liu,Md. Sahidullah,Tomi Kinnunen +2 more
- pp 85-91
Reads0
Chats0
TLDR
This paper begins the concern of enhancing the spoofing robustness of the automatic speaker verification (ASV) system, without the primary presence of a separate countermeasure module by employing three unsupervised domain adaptation techniques to optimize the back-end using the audio data in the training partition of the ASVspoof 2019 dataset.Abstract:
In this paper, we initiate the concern of enhancing the spoofing robustness of the automatic speaker verification (ASV) system, without the primary presence of a separate countermeasure module. We start from the standard ASV framework of the ASVspoof 2019 baseline and approach the problem from the back-end classifier based on probabilistic linear discriminant analysis. We employ three unsupervised domain adaptation techniques to optimize the back-end using the audio data in the training partition of the ASVspoof 2019 dataset. We demonstrate notable improvements on both logical and physical access scenarios, especially on the latter where the system is attacked by replayed audios, with a maximum of 36.1% and 5.3% relative improvement on bonafide and spoofed cases, respectively. We perform additional studies such as per-attack breakdown analysis, data composition, and integration with a countermeasure system at score-level with Gaussian back-end.read more
Citations
More filters
Proceedings ArticleDOI
SASV 2022: The First Spoofing-Aware Speaker Verification Challenge
Jee-weon Jung,Hemlata Tak,Hye-jin Shim,Hee-Soo Heo,Bong-Jin Lee,Soo-Whan Chung,Haibin Yu,Nicholas Evans,Tomi Kinnunen +8 more
TL;DR: The top-performing SASV system reduces the equal error rate of a conventional speaker verification system from 23.83% to 0.13% when assessed with target, bona fide non-target and spoofed non- target trials, a testament to the reliability of today’s state-of-the-art approaches to spoo⬁ng detection and speaker verIflcation.
Journal ArticleDOI
Voice Spoofing Countermeasures: Taxonomy, State-of-the-art, experimental analysis of generalizability, open challenges, and the way forward
TL;DR: A review of the literature on spoofing detection using hand-crafted features, deep learning, end-to-end, and universal spoo fin countermeasure solutions to detect speech synthesis, voice conversion, and replay attacks and the performance of these countermeasures on several datasets is reported.
Proceedings ArticleDOI
Mel Spectrogram Based Automatic Speaker Verification Using GMM-UBM
T. Kumar,Ramesh K. Bhukya +1 more
TL;DR: In this article , Gaussian Mixture Model (GMM) and Universal Background Model (UBM) were used for speaker verification in a text-independent speaker verification (TISV) system.
References
More filters
Proceedings Article
Auto-Encoding Variational Bayes
Diederik P. Kingma,Max Welling +1 more
TL;DR: A stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case is introduced.
Posted Content
WaveNet: A Generative Model for Raw Audio
Aaron van den Oord,Sander Dieleman,Heiga Zen,Karen Simonyan,Oriol Vinyals,Alex Graves,Nal Kalchbrenner,Andrew W. Senior,Koray Kavukcuoglu +8 more
TL;DR: This paper proposed WaveNet, a deep neural network for generating audio waveforms, which is fully probabilistic and autoregressive, with the predictive distribution for each audio sample conditioned on all previous ones.
Proceedings ArticleDOI
X-Vectors: Robust DNN Embeddings for Speaker Recognition
TL;DR: This paper uses data augmentation, consisting of added noise and reverberation, as an inexpensive method to multiply the amount of training data and improve robustness of deep neural network embeddings for speaker recognition.
Proceedings Article
Return of frustratingly easy domain adaptation
TL;DR: Correlation alignment (CORAL) as discussed by the authors minimizes domain shift by aligning the second-order statistics of source and target distributions, without requiring any target labels, and it can be implemented in four lines of Matlab code.