DiffSinger: Diffusion Acoustic Model for Singing Voice Synthesis

Singing voice synthesis (SVS) system is built to synthesize high-quality and expressive singing voice, in which the acoustic model generates the acoustic features (e.g., mel-spectrogram) given a music score. Previous singing acoustic models adopt simple loss (e.g., L1 and L2) or generative adversarial network (GAN) to reconstruct the acoustic features, while they suffer from oversmoothing and unstable training issues respectively, which hinder the naturalness of synthesized singing. In this work, we propose DiffSinger, an acoustic model for SVS based on the diffusion probabilistic model. DiffSinger is a parameterized Markov chain which iteratively converts the noise into mel-spectrogram conditioned on the music score. By implicitly optimizing variational bound, DiffSinger can be stably trained and generates realistic outputs. To further improve the voice quality, we introduce a shallow diffusion mechanism to make better use of the prior knowledge learned by the simple loss. Specifically, DiffSinger starts generation at a shallow step smaller than the total number of diffusion steps, according to the intersection of the diffusion trajectories of the ground-truth mel-spectrogram and the one predicted by a simple mel-spectrogram decoder. Besides, we train a boundary prediction network to locate the intersection and determine the shallow step adaptively. The evaluations conducted on the Chinese singing dataset demonstrate that DiffSinger outperforms state-of-the-art SVS work with a notable margin (0.11 MOS gains). Our extensional experiments also prove the generalization of DiffSinger on text-to-speech task. Equal contribution Zhejiang University Tencent AI LAB. Correspondence to: Zhou Zhao <zhaozhou@zju.edu.cn>. This is the author’s version of the work. It is posted here for your personal use. Not for redistribution.