Related papers: STAA-Net: A Sparse and Transferable Adversarial At…
In this work, we train fully convolutional networks to detect anger in speech. Since training these deep architectures requires large amounts of data and the size of emotion datasets is relatively small, we use transfer learning. However,…
Adversarial attacks for discrete data (such as texts) have been proved significantly more challenging than continuous data (such as images) since it is difficult to generate adversarial samples with gradient-based methods. Current…
Recent advancements in adversarial attacks have demonstrated their effectiveness in misleading speaker recognition models, making wrong predictions about speaker identities. On the other hand, defense techniques against speaker-adversarial…
There has been a recent surge in adversarial attacks on deep learning based automatic speech recognition (ASR) systems. These attacks pose new challenges to deep learning security and have raised significant concerns in deploying ASR…
As Spiking Neural Networks (SNNs) gain traction across various applications, understanding their security vulnerabilities becomes increasingly important. In this work, we focus on the adversarial attacks, which is perhaps the most…
Adversarial attacks are inputs that are similar to original inputs but altered on purpose. Speech-to-text neural networks that are widely used today are prone to misclassify adversarial attacks. In this study, first, we investigate the…
Affective computing is very important in the relationship between man and machine. In this paper, a system for speech emotion recognition (SER) based on speech signal is proposed, which uses new techniques in different stages of processing.…
Speech enhancement aims to obtain speech signals with high intelligibility and quality from noisy speech. Recent work has demonstrated the excellent performance of time-domain deep learning methods, such as Conv-TasNet. However, these…
Speech emotion recognition (SER) processes speech signals to detect and characterize expressed perceived emotions. Many SER application systems often acquire and transmit speech data collected at the client-side to remote cloud platforms…
Machine learning models are vulnerable to maliciously crafted Adversarial Examples (AEs). Training a machine learning model with AEs improves its robustness and stability against adversarial attacks. It is essential to develop models that…
Many deep learning algorithms can be easily fooled with simple adversarial examples. To address the limitations of existing defenses, we devised a probabilistic framework that can generate an exponentially large ensemble of models from a…
Speech enhancement deep learning systems usually require large amounts of training data to operate in broad conditions or real applications. This makes the adaptability of those systems into new, low resource environments an important…
While pre-trained automatic speech recognition (ASR) systems demonstrate impressive performance on matched domains, their performance often degrades when confronted with channel mismatch stemming from unseen recording environments and…
In this paper we investigate the ability of generative adversarial networks (GANs) to synthesize spoofing attacks on modern speaker recognition systems. We first show that samples generated with SampleRNN and WaveNet are unable to fool a…
Deep neural networks are vulnerable to adversarial attacks, where a small perturbation to an input alters the model prediction. In many cases, malicious inputs intentionally crafted for one model can fool another model. In this paper, we…
Despite the rapid development of adversarial machine learning, most adversarial attack and defense researches mainly focus on the perturbation-based adversarial examples, which is constrained by the input images. In comparison with existing…
Audio events are quite often overlapping in nature, and more prone to noise than visual signals. There has been increasing evidence for the superior performance of representations learned using sparse dictionaries for applications like…
Adversarial examples are maliciously modified inputs created to fool deep neural networks (DNN). The discovery of such inputs presents a major issue to the expansion of DNN-based solutions. Many researchers have already contributed to the…
In recent years Deep Neural Networks (DNNs) have achieved remarkable results and even showed super-human capabilities in a broad range of domains. This led people to trust in DNNs' classifications and resulting actions even in…
Existing segmentation models exhibit significant vulnerability to adversarial attacks.To improve robustness, adversarial training incorporates adversarial examples into model training. However, existing attack methods consider only global…