Publication detail

Fast Temporal Convolutions for Real-Time Audio Signal Processing

MIKLÁNEK, Š. SCHIMMEL, J.

Original Title

Fast Temporal Convolutions for Real-Time Audio Signal Processing

Type

conference paper

Language

English

Original Abstract

This paper introduces the possibilities of optimizing neural network convolutional layers for modeling nonlinear audio systems and effects. Enhanced methods for real-time dilated convolutions are presented to achieve faster signal processing times than in previous work. Due to the improved implementation of convolutional layers, a significant decrease in computational requirements was observed and validated on different configurations of single layers with dilated convolutions and WaveNet-style feedforward neural network models. In most cases, equivalent signal processing times were achieved to those using recurrent neural networks with Long Short-Term Memory units and Gated Recurrent Units, which are considered state-of-the-art in the field of black-box virtual analog modeling

Keywords

convolutional neural networks; deep learning; virtual analog modelling; nonlinear systems

Authors

MIKLÁNEK, Š.; SCHIMMEL, J.

Released

2. 9. 2022

Publisher

DAFx

Location

Vídeň

ISBN

978-3-200-08599-2

Book

Proceedings of the 25th International Conference on Digital Audio Effects (DAFx20in22)

ISBN

2413-6689

Periodical

Proceedings of the International Conference on Digital Audio Effects (DAFx)

State

Republic of Austria

Pages from

115

Pages to

121

Pages count

7

BibTex

@inproceedings{BUT178795,
  author="Štěpán {Miklánek} and Jiří {Schimmel}",
  title="Fast Temporal Convolutions for Real-Time Audio Signal Processing",
  booktitle="Proceedings of the 25th International Conference on Digital Audio Effects (DAFx20in22)",
  year="2022",
  journal="Proceedings of the International Conference on Digital Audio Effects (DAFx)",
  pages="115--121",
  publisher="DAFx",
  address="Vídeň",
  isbn="978-3-200-08599-2",
  issn="2413-6689"
}