A Real-Time Wideband Neural Vocoder at 1.6 kb/s Using LPCNet
This enables low-bitrate, high-quality speech coding for applications like telecommunications, though it is incremental as it builds on existing LPCNet models.
The paper tackled the problem of high complexity in neural speech synthesis at low bitrates by presenting a real-time neural vocoder based on LPCNet, achieving significantly higher quality than MELP at 1.6 kb/s and exceeding the quality of a waveform codec at low bitrate.
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.