This is an update on the LPCNet project, an efficient neural speech synthesizer from Mozilla’s Emerging Technologies group. LPCNet combines signal processing and deep learning to improve the efficiency of neural speech synthesis. Our recent work turns LPCNet into a very low-bitrate neural speech codec that’s actually usable on current hardware and even on phones.
LPCNet is a new project out of Mozilla’s Emerging Technologies group — an efficient neural speech synthesiser with reduced complexity over some of its predecessors. Neural speech synthesis models have already demonstrated impressive speech synthesis quality, but their computational complexity has made them hard to use in real-time, especially on phones. Our solution with LPCNet uses a combination of deep learning and digital signal processing (DSP) techniques.