Log In Sign Up

MicAugment: One-shot Microphone Style Transfer

by   Zalán Borsos, et al.

A crucial aspect for the successful deployment of audio-based models "in-the-wild" is the robustness to the transformations introduced by heterogeneous acquisition conditions. In this work, we propose a method to perform one-shot microphone style transfer. Given only a few seconds of audio recorded by a target device, MicAugment identifies the transformations associated to the input acquisition pipeline and uses the learned transformations to synthesize audio as if it were recorded under the same conditions as the target audio. We show that our method can successfully apply the style transfer to real audio and that it significantly increases model robustness when used as data augmentation in the downstream tasks.


page 1

page 2

page 3

page 4


Time Domain Neural Audio Style Transfer

A recently published method for audio style transfer has shown how to ex...

Autoencoder Based Architecture For Fast & Real Time Audio Style Transfer

Recently, there has been great interest in the field of audio style tran...

Audio style transfer

"Style transfer" among images has recently emerged as a very active rese...

Going In Style: Audio Backdoors Through Stylistic Transformations

A backdoor attack places triggers in victims' deep learning models to en...

Cover Song Synthesis by Analogy

In this work, we pose and address the following "cover song analogies" p...

Self-Supervised VQ-VAE For One-Shot Music Style Transfer

Neural style transfer, allowing to apply the artistic style of one image...

Tool- and Domain-Agnostic Parameterization of Style Transfer Effects Leveraging Pretrained Perceptual Metrics

Current deep learning techniques for style transfer would not be optimal...