Related papers: Deep Audio Prior
In this work, a novel deep neural network, designed to enhance the efficiency and effectiveness of unsupervised sound anomaly detection, is presented. The proposed model exploits an attention module and separable convolutions to identify…
In practice, deep neural networks have been found to be vulnerable to various types of noise, such as adversarial examples and corruption. Various adversarial defense methods have accordingly been developed to improve adversarial robustness…
Recent advancements in deep generative modeling make it possible to learn prior distributions from complex data that subsequently can be used for Bayesian inference. However, we find that distributions learned by deep generative models for…
There have been several successful deep learning models that perform audio super-resolution. Many of these approaches involve using preprocessed feature extraction which requires a lot of domain-specific signal processing knowledge to…
Current performance evaluation for audio source separation depends on comparing the processed or separated signals with reference signals. Therefore, common performance evaluation toolkits are not applicable to real-world situations where…
Deep convolutional networks have become a popular tool for image generation and restoration. Generally, their excellent performance is imputed to their ability to learn realistic image priors from a large number of example images. In this…
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…
With the advent of modern AI architectures, a shift has happened towards end-to-end architectures. This pivot has led to neural architectures being trained without domain-specific biases/knowledge, optimized according to the task. We in…
Dataset distillation aims to synthesize compact yet informative datasets from large ones. A significant challenge in this field is achieving a trifecta of diversity, generalization, and representativeness in a single distilled dataset.…
The majority of deep learning-based speech enhancement methods require paired clean-noisy speech data. Collecting such data at scale in real-world conditions is infeasible, which has led the community to rely on synthetically generated…
In this paper, we introduce a novel continual audio-visual sound separation task, aiming to continuously separate sound sources for new classes while preserving performance on previously learned classes, with the aid of visual guidance.…
Conventional deconvolution methods utilize hand-crafted image priors to constrain the optimization. While deep-learning-based methods have simplified the optimization by end-to-end training, they fail to generalize well to blurs unseen in…
Deep neural networks (DNNs) have achieved remarkable success in a variety of computer vision tasks, where massive labeled images are routinely required for model optimization. Yet, the data collected from the open world are unavoidably…
Deep audio representation learning using multi-modal audio-visual data often leads to a better performance compared to uni-modal approaches. However, in real-world scenarios both modalities are not always available at the time of inference,…
Recently, automatic speaker verification (ASV) based on deep learning is easily contaminated by adversarial attacks, which is a new type of attack that injects imperceptible perturbations to audio signals so as to make ASV produce wrong…
Traditional denoising methods for noise removal have largely relied on handcrafted priors, often perform well in controlled environments but struggle to address the complexity and variability of real noise. In contrast, deep learning-based…
The rapid advancement of speech synthesis and voice conversion technologies has raised significant security concerns in multimedia forensics. Although current detection models demonstrate impressive performance, they struggle to maintain…
Music source separation involves a large input field to model a long-term dependence of an audio signal. Previous convolutional neural network (CNN)-based approaches address the large input field modeling using sequentially down- and…
This paper proposes a novel framework for unsupervised audio source separation using a deep autoencoder. The characteristics of unknown source signals mixed in the mixed input is automatically by properly configured autoencoders implemented…
The computer vision literature shows that randomly weighted neural networks perform reasonably as feature extractors. Following this idea, we study how non-trained (randomly weighted) convolutional neural networks perform as feature…