We propose a two-stream convolutional network for audio recognition, that operates on time-
frequency spectrogram inputs. Following similar success in visual recognition, we learn …

We introduce a deep learning model for speech denoising, a long-standing challenge in
audio analysis arising in numerous applications. Our approach is based on a key …

In this manuscript, we propose a novel method to perform audio inpainting, ie, the
restoration of audio signals presenting multiple missing parts. Audio inpainting can be …

Abstract Models for audio generation are typically trained on hours of recordings. Here, we
illustrate that capturing the essence of an audio source is typically possible from as little as a …

Growing research demonstrates that synthetic failure modes imply poor generalization. We
compare commonly used audio-to-audio losses on a synthetic benchmark, measuring the …

While neural network models are making significant progress in piano transcription, they are
becoming more resource-consuming due to requiring larger model size and more …

Convolutional neural networks contain strong priors for generating natural looking images
[1]. These priors enable image denoising, super resolution, and inpainting in an …

Inducing symmetry equivariance in deep neural architectures has resolved into improved
data efficiency and generalization. In this work, we utilize the concept of scale and …

Abstract Representation learning has been increasing its impact on the research and
practice of machine learning, since it enables to learn representations that can apply to …

Anomaly detection is a task of identifying samples that significantly differ from the majority.
However, most typical anomaly detection methods often prioritize accuracy over …