Related papers: Generalized Fake Audio Detection via Deep Stable L…

Noisy labels are an unavoidable consequence of labeling processes and detecting them is an important step towards preventing performance degradations in Convolutional Neural Networks. Discarding noisy labels avoids a harmful memorization,…

In the context of supervised learning of a function by a neural network, we claim and empirically verify that the neural network yields better results when the distribution of the data set focuses on regions where the function to learn is…

In this paper, we propose an enhanced audio-visual deep detection method. Recent methods in audio-visual deepfake detection mostly assess the synchronization between audio and visual features. Although they have shown promising results,…

Training deep neural networks with noise and data heterogeneity is a major challenge. We introduce Lightweight Learnable Adaptive Weighting (LiLAW), a method that dynamically adjusts the loss weight of each training sample based on its…

Recent advances in speech deepfake detection (SDD) have significantly improved artifacts-based detection in spoofed speech. However, most models overlook speech naturalness, a crucial cue for distinguishing bona fide speech from spoofed…

Training deep neural networks requires many training samples, but in practice training labels are expensive to obtain and may be of varying quality, as some may be from trusted expert labelers while others might be from heuristics or other…

We propose SWA-Gaussian (SWAG), a simple, scalable, and general purpose approach for uncertainty representation and calibration in deep learning. Stochastic Weight Averaging (SWA), which computes the first moment of stochastic gradient…

Unsupervised domain adaptation (UDA) aims to improve the classification performance on an unlabeled target domain by leveraging information from a fully labeled source domain. Recent approaches explore domain-invariant and…

In this paper, we propose a new method called Self-Training with Dynamic Weighting (STDW), which aims to enhance robustness in Gradual Domain Adaptation (GDA) by addressing the challenge of smooth knowledge migration from the source to the…

While computer vision and machine learning have made great progress, their robustness is still challenged by two key issues: data distribution shift and label noise. When domain generalization (DG) encounters noise, noisy labels further…

Advances in speech synthesis technologies, like text-to-speech (TTS) and voice conversion (VC), have made detecting deepfake speech increasingly challenging. Spoofing countermeasures often struggle to generalize effectively, particularly…

Deep learning with noisy labels is a challenging task. Recent prominent methods that build on a specific sample selection (SS) strategy and a specific semi-supervised learning (SSL) model achieved state-of-the-art performance. Intuitively,…

In speech deepfake detection, one of the critical aspects is developing detectors able to generalize on unseen data and distinguish fake signals across different datasets. Common approaches to this challenge involve incorporating diverse…

Deep learning techniques for medical image analysis usually suffer from the domain shift between source and target data. Most existing works focus on unsupervised domain adaptation (UDA). However, in practical applications, privacy issues…

Presently the most successful approaches to semi-supervised learning are based on consistency regularization, whereby a model is trained to be robust to small perturbations of its inputs and parameters. To understand consistency…

The performance of automatic speaker verification (ASV) and anti-spoofing drops seriously under real-world domain mismatch conditions. The relaxed instance frequency-wise normalization (RFN), which normalizes the frequency components based…

Audio deepfake detection (ADD) is crucial to combat the misuse of speech synthesized from generative AI models. Existing ADD models suffer from generalization issues, with a large performance discrepancy between in-domain and out-of-domain…

With rapid advances in audio-visual generative models, reliable forgery detection becomes increasingly critical. Existing methods for audio-visual deepfake detection typically rely on cross-modal inconsistencies. In singing, rhythmic…

Audio deepfake detection has become a pivotal task over the last couple of years, as many recent speech synthesis and voice cloning systems generate highly realistic speech samples, thus enabling their use in malicious activities. In this…

Audio deepfake detection has recently garnered public concern due to its implications for security and reliability. Traditional deep learning methods have been widely applied to this task but often lack generalisability when confronted with…