In this paper, we develop a new multi-singer Chinese neural singing voice
synthesis (SVS) system named WeSinger. To improve the accuracy and naturalness
of synthesized singing voice, we design several specifical modules and
techniques: 1) A deep bi-directional LSTM-based duration model with multi-scale
rhythm loss and post-processing step; 2) A Transformer-alike acoustic model
with progressive pitch-weighted decoder loss; 3) a 24 kHz pitch-aware LPCNet
neural vocoder to produce high-quality singing waveforms; 4) A novel data
augmentation method with multi-singer pre-training for stronger robustness and
naturalness. To our knowledge, WeSinger is the first SVS system to adopt 24 kHz
LPCNet and multi-singer pre-training simultaneously. Both quantitative and
qualitative evaluation results demonstrate the effectiveness of WeSinger in
terms of accuracy and naturalness, and WeSinger achieves state-of-the-art
performance on the recent public Chinese singing corpus
Opencpop\footnote{this https URL}. Some synthesized singing
samples are available online\footnote{this https URL}.

本文介绍了一种新型的多歌手中文神经唱歌声合成系统 WeSinger，它采用了 24 kHz LPCNet 和多歌手预训练，通过定制的模块和技术大幅提高了合成歌声的准确性和自然度。该系统在公共中文唱歌语料库 Opencpop 上取得了最先进的性能表现。