Related papers: Adversarial Permutation Invariant Training for Uni…
For many computer vision applications such as image captioning, visual question answering, and person search, learning discriminative feature representations at both image and text level is an essential yet challenging problem. Its…
Deep learning models are vulnerable to adversarial examples and make incomprehensible mistakes, which puts a threat on their real-world deployment. Combined with the idea of adversarial training, preprocessing-based defenses are popular and…
We introduce a new paradigm for single-channel target source separation where the sources of interest can be distinguished using non-mutually exclusive concepts (e.g., loudness, gender, language, spatial location, etc). Our proposed…
Deep neural networks (DNNs) have risen to prominence as key solutions in numerous AI applications for earth observation (AI4EO). However, their susceptibility to adversarial examples poses a critical challenge, compromising the reliability…
In this study, we propose a timbre-reserved adversarial attack approach for speaker identification (SID) to not only exploit the weakness of the SID model but also preserve the timbre of the target speaker in a black-box attack setting.…
Deep neural networks (DNNs) are vulnerable to adversarial examples crafted by well-designed perturbations. This could lead to disastrous results on critical applications such as self-driving cars, surveillance security, and medical…
We consider the problem of audio voice separation for binaural applications, such as earphones and hearing aids. While today's neural networks perform remarkably well (separating $4+$ sources with 2 microphones) they assume a known or fixed…
Universal sound separation (USS) aims to extract arbitrary types of sounds from real-world recordings. This can be achieved by language-queried target sound extraction (TSE), which typically consists of two components: a query network that…
Adversarial examples tremendously threaten the availability and integrity of machine learning-based systems. While the feasibility of such attacks has been observed first in the domain of image processing, recent research shows that speech…
Adversarial training is a technique for training robust machine learning models. To encourage robustness, it iteratively computes adversarial examples for the model, and then re-trains on these examples via some update rule. This work…
Audio source separation is usually achieved by estimating the short-time Fourier transform (STFT) magnitude of each source, and then applying a spectrogram inversion algorithm to retrieve time-domain signals. In particular, the multiple…
Consonant and vowel reduction are often encountered in speech, which might cause performance degradation in automatic speech recognition (ASR). Our recently proposed learning strategy based on masking, Phone Masking Training (PMT),…
Training models that are robust to data domain shift has gained an increasing interest both in academia and industry. Question-Answering language models, being one of the typical problem in Natural Language Processing (NLP) research, has…
Supervised deep learning approaches to underdetermined audio source separation achieve state-of-the-art performance but require a dataset of mixtures along with their corresponding isolated source signals. Such datasets can be extremely…
Computational paralinguistic analysis is increasingly being used in a wide range of cyber applications, including security-sensitive applications such as speaker verification, deceptive speech detection, and medical diagnostics. While…
In this paper, we present an approach to improve the robustness of BERT language models against word substitution-based adversarial attacks by leveraging adversarial perturbations for self-supervised contrastive learning. We create a…
Discriminative models for source separation have recently been shown to produce impressive results. However, when operating on sources outside of the training set, these models can not perform as well and are cumbersome to update. Classical…
Generalization and robustness are both key desiderata for designing machine learning methods. Adversarial training can enhance robustness, but past work often finds it hurts generalization. In natural language processing (NLP), pre-training…
Deep neural networks have been demonstrated to be vulnerable to adversarial noise, promoting the development of defense against adversarial attacks. Motivated by the fact that adversarial noise contains well-generalizing features and that…
Deep learning voice models are commonly used nowadays, but the safety processing of personal data, such as human identity and speech content, remains suspicious. To prevent malicious user identification, speaker anonymization methods were…