The term “differentiable digital signal processing” describes a family of techniques in which
loss function gradients are backpropagated through digital signal processors, facilitating …

We present a framework that can impose the audio effects and production style from one
recording to another by example with the goal of simplifying the audio production process …

Artificial reverberation (AR) models play a central role in various audio applications.
Therefore, estimating the AR model parameters (ARPs) of a reference reverberation is a …

We present auraloss 1, a PyTorch package that implements time and frequency domain loss
functions designed for audio generation tasks. The package provides a straightforward …

A vocoder is a conditional audio generation model that converts acoustic features such as
mel-spectrograms into waveforms. Taking inspiration from Differentiable Digital Signal …

Music mixing traditionally involves recording instruments in the form of clean, individual
tracks and blending them into a final mixture using audio effects and expert knowledge (eg …

Deep learning approaches have demonstrated success in modeling analog audio effects.
Nevertheless, challenges remain in modeling more complex effects that involve time-varying …

Recurrent neural networks (RNNs) have demonstrated impressive results for virtual analog
modeling of audio effects. These networks process time-domain audio signals using a series …

Replicating analog device circuits through neural audio effect modeling has garnered
increasing interest in recent years. Existing work has predominantly focused on a one-to …

A method to retrieve the parameters used to create a multitrack mix using only raw tracks
and the stereo mixdown is presented. This method is able to model linear time-invariant …