From 7dc99429e246cca614708b5aa4990d827bacce2c Mon Sep 17 00:00:00 2001 From: Jean-Marc Valin Date: Fri, 20 Sep 2024 23:59:17 -0400 Subject: [PATCH] Link to FARGAN --- README.md | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/README.md b/README.md index 930b043..f516c36 100644 --- a/README.md +++ b/README.md @@ -1,3 +1,18 @@ +**Important**: LPCNet is no longer being actively developed. It will remain +available but for most applications, users are encouraged to switch to the +Framewise Autoregressive GAN (FARGAN). FARGAN achieves better quality than +LPCNet with just 600 MFLOPS complexity. That's 1/5 of the complexity of the +most optimized LPCNet and 1/20 of the original LPCNet. + +- J.-M. Valin, A. Mustafa, Jan Büthe, [Very Low Complexity Speech Synthesis Using Framewise Autoregressive GAN (FARGAN) with Pitch Prediction](https://arxiv.org/pdf/2405.21069), IEEE Signal Processing Letters, 2024, arXiv:2405.21069. + +See our [demo page](https://ahmed-fau.github.io/fargan_demo/) for comparisons +with LPCNet, HiFi-GAN, CARGAN and FWGAN. +The PyTorch [source code](https://gitlab.xiph.org/xiph/opus/-/tree/main/dnn/torch/fargan) +along with an optimized C implementation are available as part of the larger +[Opus codec](https://opus-codec.org) implementation (FARGAN is used for PLC +and deep redundancy within Opus). + # LPCNet Low complexity implementation of the WaveRNN-based LPCNet algorithm, as described in: