recurrent neural network for audio noise reduction
Project homepage: https://jmvalin.ca/demo/rnnoise
Description
RNNoise is a noise suppression library based on a recurrent neural network.
A description of the algorithm is provided in the following paper:
J.-M. Valin, A Hybrid DSP/Deep Learning Approach to Real-Time Full-Band Speech
Enhancement, Proceedings of IEEE Multimedia Signal Processing (MMSP) Workshop,
arXiv:1709.08243, 2018.
https://arxiv.org/pdf/1709.08243
While it is meant to be used as a library, the code for a simple command-line
tool is provided as an example. It operates on RAW 16-bit (machine endian) mono
PCM files sampled at 48 kHz.
Package information
- Ports path
- audio/rnnoise
- Package architecture
- amd64
- Maintainer
- Klemens Nanni <kn@openbsd.org>
- Categories
- audio
- Available flavors
- None listed
Ports list build and test dependencies as well as runtime dependencies. pkg_add selects those needed for installation.
Direct dependencies
Build
Used by (4 dependency relationships)
Includes library, runtime, build and test dependencies.