Approximating Ballistics in a Differentiable Dynamic Range Compressor

Colonel JT, Reiss JD. Approximating Ballistics in a Differentiable Dynamic Range Compressor. In: AES Convention 153. Audio Engineering Society; 2022. Paper 33. Available from: https://aes.org/publications/elibrary-page/?id=21915

@inproceedings{Colonel2022_21915,
  author = {Colonel, Joseph, T. and Reiss, Joshua D.},
  title = {{Approximating Ballistics in a Differentiable Dynamic Range Compressor}},
  booktitle = {AES Convention 153},
  note = {Paper 33},
  year = {2022},
  month = oct,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=21915}
}

TY  - CPAPER
TI  - Approximating Ballistics in a Differentiable Dynamic Range Compressor
AU  - Colonel, Joseph, T.
AU  - Reiss, Joshua D.
T2  - AES Convention 153
M1  - Paper 33
PY  - 2022
DA  - 2022/10/06
UR  - https://aes.org/publications/elibrary-page/?id=21915
PB  - Audio Engineering Society
LA  - en
AB  - We present a dynamic range compressor with ballistics implemented in a differentiable framework that can be used for differentiable digital signal processing tasks. This compressor can update the values of its threshold, compression ratio, knee width, makeup gain, attack time, and release time using stochastic gradient descent and backpropagation techniques. The performance of this technique is evaluated on a reverse engineering of audio effects task, in which the parameter settings of a dynamic range compressor are inferred from a dry and wet pair of audio samples. Techniques for initializing the parameter estimates in this reverse engineering task are outlined and discussed.
ER  -