Bunched LPCNet2: Efficient Neural Vocoders Covering Devices from Cloud to Edge
Sangjun Park, Kihyun Choo, Joohyung Lee, Anton V. Porov, Konstantin Osipov, June Sig Sung · Interspeech 2022 · 2022
Text-to-Speech (TTS) services that run on edge devices have many advantages compared to cloud TTS, e.g., latency and privacy issues.However, neural vocoders with a low complexity and small model footprint inevitably generate annoying sounds.This study proposes a Bunched LPCNet2, an improved LPCNet architecture that provides highly efficient performance in high-quality for cloud servers and in a lowcomplexity for low-resource edge devices.Single logistic distribution achieves computational efficiency, and insightful tricks reduce the model footprint while maintaining speech quality.A DualRate architecture, which generates a lower sampling rate from a prosody model, is also proposed to reduce maintenance costs.The experiments demonstrate that Bunched LPCNet2 generates satisfactory speech quality with a model footprint of 1.1MB while operating faster than real-time on a RPi 3B.Our audio samples are available at https://srtts.github.io/bunchedLPCNet2.