Related papers: Pseudo-Siamese Network based Timbre-reserved Black…

We propose a test-time defense mechanism against adversarial attacks: imperceptible image perturbations that significantly alter the predictions of a model. Unlike existing methods that rely on feature filtering or smoothing, which can lead…

Adversarial attacks refer to a set of methods that perturb the input to a classification model in order to fool the classifier. In this paper we apply different gradient based adversarial attack algorithms on five deep learning models…

A significant challenge in sound event detection (SED) is the effective utilization of unlabeled data, given the limited availability of labeled data due to high annotation costs. Semi-supervised algorithms rely on labeled data to learn…

Deep learning has made significant breakthroughs in many fields, including electroencephalogram (EEG) based brain-computer interfaces (BCIs). However, deep learning models are vulnerable to adversarial attacks, in which deliberately…

Deep neural networks (DNNs) have been widely and successfully adopted and deployed in various applications of speech recognition. Recently, a few works revealed that these models are vulnerable to backdoor attacks, where the adversaries can…

Anomalous Sound Detection (ASD) is often formulated as a machine attribute classification task, a strategy necessitated by the common scenario where only normal data is available for training. However, the exhaustive collection of machine…

Speech models are often trained on sensitive data in order to improve model performance, leading to potential privacy leakage. Our work considers noise masking attacks, introduced by Amid et al. 2022, which attack automatic speech…

Speaker recognition, recognizing speaker identities based on voice alone, enables important downstream applications, such as personalization and authentication. Learning speaker representations, in the context of supervised learning,…

Voice authentication has become an integral part in security-critical operations, such as bank transactions and call center conversations. The vulnerability of automatic speaker verification systems (ASVs) to spoofing attacks instigated the…

Extensive research has revealed that adversarial examples (AE) pose a significant threat to voice-controllable smart devices. Recent studies have proposed black-box adversarial attacks that require only the final transcription from an…

Voice Processing Systems (VPSes), now widely deployed, have been made significantly more accurate through the application of recent advances in machine learning. However, adversarial machine learning has similarly advanced and has been used…

Adversarial attack on question answering systems over tabular data (TableQA) can help evaluate to what extent they can understand natural language questions and reason with tables. However, generating natural language adversarial questions…

Dysarthric speech reconstruction (DSR), which aims to improve the quality of dysarthric speech, remains a challenge, not only because we need to restore the speech to be normal, but also must preserve the speaker's identity. The speaker…

Automatic speech recognition (ASR) systems are known to be vulnerable to adversarial attacks. This paper addresses detection and defence against targeted white-box attacks on speech signals for ASR systems. While existing work has utilised…

This paper presents an adversarial learning method for recognition-synthesis based non-parallel voice conversion. A recognizer is used to transform acoustic features into linguistic representations while a synthesizer recovers output…

We propose a method to generate audio adversarial examples that can attack a state-of-the-art speech recognition model in the physical world. Previous work assumes that generated adversarial examples are directly fed to the recognition…

The strategy of combining diffusion-based generative models with classifiers continues to demonstrate state-of-the-art performance on adversarial robustness benchmarks. Known as adversarial purification, this exploits a diffusion model's…

Target-Speaker Voice Activity Detection (TS-VAD) is the task of detecting the presence of speech from a known target-speaker in an audio frame. Recently, deep neural network-based models have shown good performance in this task. However,…

Despite the significant improvements in speaker recognition enabled by deep neural networks, unsatisfactory performance persists under noisy environments. In this paper, we train the speaker embedding network to learn the "clean" embedding…

Self-supervised speech model is a rapid progressing research topic, and many pre-trained models have been released and used in various down stream tasks. For speech anti-spoofing, most countermeasures (CMs) use signal processing algorithms…