Opencpop
Emerging5papers using it
2022first seen
The 'Opencpop' dataset is a publicly available singing dataset used to evaluate the performance of singing voice synthesis models, particularly in addressing challenges related to data scarcity and imbalanced pitch distributions.
Papers using Opencpop (5)
- Robust Training of Singing Voice Synthesis Using Prior and Posterior UncertaintySmoothSinger: A Conditional Diffusion Model for Singing Voice Synthesis with Multi-Resolution ArchitectureOpencpop: A High-Quality Open Source Chinese Popular Song Corpus for
Singing Voice SynthesisWeSinger: Data-augmented Singing Voice Synthesis with Auxiliary LossesSiFiSinger: A High-Fidelity End-to-End Singing Voice Synthesizer based
on Source-filter Model