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 low-complexity 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.

翻译：与云层TTS相比,在边缘设备上运行的文本到语音服务(TTS)具有许多优势,例如潜伏和隐私问题。然而,低复杂度和小模型足迹的神经电动电动器不可避免地会产生令人烦恼的声音。本研究报告建议建立一个组合式LPCNet2, 一个经过改进的LPCNet2 结构,为云层服务器和低资源边缘装置提供高质量的高效性能,单一后勤分配达到计算效率,有洞察力的技巧在保持语音质量的同时减少了模型足迹。一个双轨结构,从手动模型中产生较低的采样率,也提议降低维护费用。实验表明,集式LPCNet2产生令人满意的语音质量,模型足迹为1.1MB,同时在RP3B上运行速度比实时快。我们的音频样本可在https://srtts.github.io/bunchedLPCNet2上查阅。