MicAugment: One-shot Microphone Style Transfer
This addresses robustness issues for audio-based models in real-world deployment, but it is incremental as it builds on existing style transfer and data augmentation techniques.
The paper tackles the problem of audio model robustness to different microphone conditions by proposing a one-shot microphone style transfer method, which synthesizes audio as if recorded by a target device and significantly improves model robustness in downstream tasks.
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.