LPCNet: linear prediction with a recurrent neural excitation model

What changed

Combined a linear-prediction spectral envelope with a WaveRNN-derived neural excitation model to reduce speech-synthesis complexity.

Scientific scope

Combined a linear-prediction spectral envelope with a WaveRNN-derived neural excitation model to reduce speech-synthesis complexity. Inherits linear predictive coding and WaveRNN; delta is their specific low-complexity integration. Reported operation budgets and quality depend on conditioning/data/hardware. This original is LPCNet, not WaveGlow.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Inherits linear predictive coding and WaveRNN; delta is their specific low-complexity integration. Reported operation budgets and quality depend on conditioning/data/hardware. This original is LPCNet, not WaveGlow.

Contributors

• Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.

• LPCNet: Improving Neural Speech Synthesis Through Linear Prediction

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction