相关论文: Adversarial Data Augmentation for Robust Speaker V…

We propose a novel adversarial speaker adaptation (ASA) scheme, in which adversarial learning is applied to regularize the distribution of deep hidden features in a speaker-dependent (SD) deep neural network (DNN) acoustic model to be close…

Adversarial perturbations pose a significant threat to deep learning models. Adversarial Training (AT), the predominant defense method, faces challenges of high computational costs and a degradation in standard performance. While data…

Recent advances in computer vision take advantage of adversarial data augmentation to ameliorate the generalization ability of classification models. Here, we present an effective and efficient alternative that advocates adversarial…

Data augmentation is commonly used for generating additional data from the available training data to achieve a robust estimation of the parameters of complex models like the one for speaker verification (SV), especially for under-resourced…

Many speech enhancement methods try to learn the relationship between noisy and clean speech, obtained using an acoustic room simulator. We point out several limitations of enhancement methods relying on clean speech targets; the goal of…

Data augmentation (DA) is fundamental against overfitting in large convolutional neural networks, especially with a limited training dataset. In images, DA is usually based on heuristic transformations, like geometric or color…

In this paper, we perform an in-depth study of how data augmentation techniques improve synthetic or spoofed audio detection. Specifically, we propose methods to deal with channel variability, different audio compressions, different…

Adversarial training of Deep Neural Networks is known to be significantly more data-hungry when compared to standard training. Furthermore, complex data augmentations such as AutoAugment, which have led to substantial gains in standard…

Data augmentation is conventionally used to inject robustness in Speaker Verification systems. Several recently organized challenges focus on handling novel acoustic environments. Deep learning based speech enhancement is a modern solution…

The speech enhancement task usually consists of removing additive noise or reverberation that partially mask spoken utterances, affecting their intelligibility. However, little attention is drawn to other, perhaps more aggressive signal…

In this article we propose a novel approach for adapting speaker embeddings to new domains based on adversarial training of neural networks. We apply our embeddings to the task of text-independent speaker verification, a challenging,…

In speech deepfake detection (SDD), data augmentation (DA) is commonly used to improve model generalization across varied speech conditions and spoofing attacks. However, during training, the backpropagated gradients from original and…

Recent works have demonstrated convolutional neural networks are vulnerable to adversarial examples, i.e., inputs to machine learning models that an attacker has intentionally designed to cause the models to make a mistake. To improve the…

Transcribed datasets typically contain speaker identity for each instance in the data. We investigate two ways to incorporate this information during training: Multi-Task Learning and Adversarial Learning. In multi-task learning, the goal…

The use of deep networks to extract embeddings for speaker recognition has proven successfully. However, such embeddings are susceptible to performance degradation due to the mismatches among the training, enrollment, and test conditions.…

In this paper we investigate the use of adversarial domain adaptation for addressing the problem of language mismatch between speaker recognition corpora. In the context of speaker verification, adversarial domain adaptation methods aim at…

Data augmentation (DA) techniques aim to increase data variability, and thus train deep networks with better generalisation. The pioneering AutoAugment automated the search for optimal DA policies with reinforcement learning. However,…

Modern speaker recognition system relies on abundant and balanced datasets for classification training. However, diverse defective datasets, such as partially-labelled, small-scale, and imbalanced datasets, are common in real-world…

Vision-language models (VLMs) are vulnerable to adversarial image perturbations. Existing works based on adversarial training against task-specific adversarial examples are computationally expensive and often fail to generalize to unseen…

Visual Question Answering (VQA) has achieved great success thanks to the fast development of deep neural networks (DNN). On the other hand, the data augmentation, as one of the major tricks for DNN, has been widely used in many computer…