Neural Speech Synthesis on a Shoestring: Improving the Efficiency of LPCNet
This incremental improvement makes real-time neural speech synthesis more accessible on a wide variety of devices, including phones and embedded systems.
The paper tackles the high computational complexity of neural speech synthesis by improving the efficiency of LPCNet, resulting in a 2.5x speed increase while enhancing synthesis quality.
Neural speech synthesis models can synthesize high quality speech but typically require a high computational complexity to do so. In previous work, we introduced LPCNet, which uses linear prediction to significantly reduce the complexity of neural synthesis. In this work, we further improve the efficiency of LPCNet -- targeting both algorithmic and computational improvements -- to make it usable on a wide variety of devices. We demonstrate an improvement in synthesis quality while operating 2.5x faster. The resulting open-source LPCNet algorithm can perform real-time neural synthesis on most existing phones and is even usable in some embedded devices.