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

In recent years, a variety of tasks have been accomplished by deep reinforcement learning (DRL). However, when applying DRL to tasks in a real-world environment, designing an appropriate reward is difficult. Rewards obtained via actual…

Noisy labels are ubiquitous in real-world datasets, especially in the large-scale ones derived from crowdsourcing and web searching. It is challenging to train deep neural networks with noisy datasets since the networks are prone to…

Deepfake speech detection presents a growing challenge as generative audio technologies continue to advance. We propose a hybrid training framework that advances detection performance through novel augmentation strategies. First, we…

The homogeneity, or more generally, the similarity between source domains and a target domain seems to be essential to a positive transfer learning. In practice, however, the similarity condition is difficult to check and is often violated.…

Speaker representation learning is crucial for voice recognition systems, with recent advances in self-supervised approaches reducing dependency on labeled data. Current two-stage iterative frameworks, while effective, suffer from…

This paper conducts a comprehensive layer-wise analysis of self-supervised learning (SSL) models for audio deepfake detection across diverse contexts, including multilingual datasets (English, Chinese, Spanish), partial, song, and…

Approximately 1.2% of the world's population has impaired voice production. As a result, automatic dysphonic voice detection has attracted considerable academic and clinical interest. However, existing methods for automated voice assessment…

Deep Learning (DL) models achieve great successes in many domains. However, DL models increasingly face safety and robustness concerns, including noisy labeling in the training stage and feature distribution shifts in the testing stage.…

Training deep networks with noisy labels leads to poor generalization and degraded accuracy due to overfitting to label noise. Existing approaches for learning with noisy labels often rely on the availability of a clean subset of data. By…

Long-tailed learning has attracted much attention recently, with the goal of improving generalisation for tail classes. Most existing works use supervised learning without considering the prevailing noise in the training dataset. To move…

This paper presents a score-based weighted likelihood estimator (SWLE) for robust estimations of generalized linear model (GLM) for insurance loss data. The SWLE exhibits a limited sensitivity to the outliers, theoretically justifying its…

Large language model pre-training typically exhibits a two-phase trajectory: a fast initial loss drop followed by a prolonged slow improvement. We identify an underlying spectral phenomenon, Stability of Singular Distribution (SoSD), where…

Fake speech detection systems have become a necessity to combat against speech deepfakes. Current systems exhibit poor generalizability on out-of-domain speech samples due to lack to diverse training data. In this paper, we attempt to…

Traditional federated learning (FL) algorithms operate under the assumption that the data distributions at training (source domains) and testing (target domain) are the same. The fact that domain shifts often occur in practice necessitates…

Deepfake audio presents a growing threat to digital security, due to its potential for social engineering, fraud, and identity misuse. However, existing detection models suffer from poor generalization across datasets, due to implicit…

Pseudo-Labeling has emerged as a simple yet effective technique for semi-supervised object detection (SSOD). However, the inevitable noise problem in pseudo-labels significantly degrades the performance of SSOD methods. Recent advances…

Semi-Supervised Learning (SSL) under class distribution mismatch aims to tackle a challenging problem wherein unlabeled data contain lots of unknown categories unseen in the labeled ones. In such mismatch scenarios, traditional SSL suffers…

For many machine learning algorithms, two main assumptions are required to guarantee performance. One is that the test data are drawn from the same distribution as the training data, and the other is that the model is correctly specified.…

Sampling rate offsets (SROs) between devices in a heterogeneous wireless acoustic sensor network (WASN) can hinder the ability of distributed adaptive algorithms to perform as intended when they rely on coherent signal processing. In this…

We propose a framework for learning calibrated uncertainties under domain shifts, where the source (training) distribution differs from the target (test) distribution. We detect such domain shifts via a differentiable density ratio…