The single-speaker singing voice synthesis (SVS) usually underperforms at
pitch values that are out of the singer's vocal range or associated with
limited training samples. Based on our previous work, this work proposes a
melody-unsupervised multi-speaker pre-training method conducted on a
multi-singer dataset to enhance the vocal range of the single-speaker, while
not degrading the timbre similarity. This pre-training method can be deployed
to a large-scale multi-singer dataset, which only contains audio-and-lyrics
pairs without phonemic timing information and pitch annotation. Specifically,
in the pre-training step, we design a phoneme predictor to produce the
frame-level phoneme probability vectors as the phonemic timing information and
a speaker encoder to model the timbre variations of different singers, and
directly estimate the frame-level f0 values from the audio to provide the pitch
information. These pre-trained model parameters are delivered into the
fine-tuning step as prior knowledge to enhance the single speaker's vocal
range. Moreover, this work also contributes to improving the sound quality and
rhythm naturalness of the synthesized singing voices. It is the first to
introduce a differentiable duration regulator to improve the rhythm naturalness
of the synthesized voice, and a bi-directional flow model to improve the sound
quality. Experimental results verify that the proposed SVS system outperforms
the baseline on both sound quality and naturalness.

基于先前的研究，在一个多歌手的数据集上进行的旋律无监督多说话人预训练方法，提高了单个说话人的声域，同时不降低音色相似性。这种预训练方法可以应用于只包含音频和歌词对的大规模多歌手数据集，并改善了合成歌声的音质和节奏自然度。

使用无旋律监督预训练提升单音人声合成的音域

Enhancing the vocal range of single-speaker singing voice synthesis with  melody-unsupervised pre-training

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。