We present a lightweight adaptable neural TTS system with high quality
output. The system is composed of three separate neural network blocks: prosody
prediction, acoustic feature prediction and Linear Prediction Coding Net as a
neural vocoder. This system can synthesize speech with close to natural quality
while running 3 times faster than real-time on a standard CPU. The modular
setup of the system allows for simple adaptation to new voices with a small
amount of data. We first demonstrate the ability of the system to produce high
quality speech when trained on large, high quality datasets. Following that, we
demonstrate its adaptability by mimicking unseen voices using 5 to 20 minutes
long datasets with lower recording quality. Large scale Mean Opinion Score
quality and similarity tests are presented, showing that the system can adapt
to unseen voices with quality gap of 0.12 and similarity gap of 3% compared to
natural speech for male voices and quality gap of 0.35 and similarity of gap of
9 % for female voices.

本研究提出了一种轻量级的适应性神经 TTS 系统，采用三个单独的神经网络块来实现韵律预测、声学特征预测和线性预测编码神经声码器，性能接近自然语音合成，同时在标准 CPU 上实时性能比真实速度快 3 倍，系统的模块化设置使得可适应新的语音，只需要少量的数据，在大量实验中展示了系统的高质量和适应性，提高了 0.12 的质量差距和 3% 的相似性差距，可适应未见的声音和性别的合成。