Low-Resource Cross-Domain Singing Voice Synthesis via Reduced Self-Supervised Speech Representations
This addresses the challenge of low-resource singing voice synthesis for applications like karaoke, though it is incremental as it builds on existing self-supervised and multi-task learning methods.
The paper tackles the problem of singing voice synthesis without using singing data by proposing Karaoker-SSL, a model trained only on text and speech data, which achieves competitive performance with a mean opinion score of 3.8 on a cross-domain dataset.
In this paper, we propose a singing voice synthesis model, Karaoker-SSL, that is trained only on text and speech data as a typical multi-speaker acoustic model. It is a low-resource pipeline that does not utilize any singing data end-to-end, since its vocoder is also trained on speech data. Karaoker-SSL is conditioned by self-supervised speech representations in an unsupervised manner. We preprocess these representations by selecting only a subset of their task-correlated dimensions. The conditioning module is indirectly guided to capture style information during training by multi-tasking. This is achieved with a Conformer-based module, which predicts the pitch from the acoustic model's output. Thus, Karaoker-SSL allows singing voice synthesis without reliance on hand-crafted and domain-specific features. There are also no requirements for text alignments or lyrics timestamps. To refine the voice quality, we employ a U-Net discriminator that is conditioned on the target speaker and follows a Diffusion GAN training scheme.