A Real-Time Wideband Neural Vocoder at 1.6 kb/s Using LPCNet

Jean-Marc Valin, Jan Skoglund
3/28/2019
eess.AScs.LGcs.SD

Official code: xiph/LPCNet (1,223 stars, BSD-3-Clause, last commit 2024-09-21).

Abstract

Neural speech synthesis algorithms are a promising new approach for coding speech at very low bitrate. They have so far demonstrated quality that far exceeds traditional vocoders, at the cost of very high complexity. In this work, we present a low-bitrate neural vocoder based on the LPCNet model. The use of linear prediction and sparse recurrent networks makes it possible to achieve real-time operation on general-purpose hardware. We demonstrate that LPCNet operating at 1.6 kb/s achieves significantly higher quality than MELP and that uncompressed LPCNet can exceed the quality of a waveform codec operating at low bitrate. This opens the way for new codec designs based on neural synthesis models.

View on arXivView PDF

Code Implementations(1)

xiph/LPCNetOfficial100%
BSD-3-Clause

Efficient neural speech synthesis

1,223306C, M4Oct 25, 20182 years agoBSD-3-Clause

Similar Papers

PSCodec: A Series of High-Fidelity Low-bitrate Neural Speech Codecs Leveraging Prompt Encoders

88% match2024

Ultra-Low-Bitrate Speech Coding with Pretrained Transformers

88% match2022

LPCNet: Improving Neural Speech Synthesis Through Linear Prediction

86% match1 repo1.2k2018

NESC: Robust Neural End-2-End Speech Coding with GANs

84% match2022

Ultra-lightweight Neural Differential DSP Vocoder For High Quality Speech Synthesis

84% match2024

Probing Low Frame Rate Degradation in Neural Audio Codecs

84% match2026

Cite this paper

@article{valin2019realtime,
  title  = {A Real-Time Wideband Neural Vocoder at 1.6 kb/s Using LPCNet},
  author = {Jean-Marc Valin and Jan Skoglund},
  year   = {2019},
  eprint = {1903.12087},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1903.12087}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1903.12087.svg)](https://codeofpaper.com/paper/1903.12087)

Discussion