Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis
This provides a publicly available dataset to address the lack of resources for singing voice synthesis in Mandarin, though it is incremental as it builds on existing corpus creation efforts.
The paper introduces Opencpop, a high-quality open-source Mandarin singing corpus for singing voice synthesis, consisting of 100 songs with phonetic annotations, and demonstrates its reliability by achieving a 3.70 mean opinion score with baseline models.
This paper introduces Opencpop, a publicly available high-quality Mandarin singing corpus designed for singing voice synthesis (SVS). The corpus consists of 100 popular Mandarin songs performed by a female professional singer. Audio files are recorded with studio quality at a sampling rate of 44,100 Hz and the corresponding lyrics and musical scores are provided. All singing recordings have been phonetically annotated with phoneme boundaries and syllable (note) boundaries. To demonstrate the reliability of the released data and to provide a baseline for future research, we built baseline deep neural network-based SVS models and evaluated them with both objective metrics and subjective mean opinion score (MOS) measure. Experimental results show that the best SVS model trained on our database achieves 3.70 MOS, indicating the reliability of the provided corpus. Opencpop is released to the open-source community WeNet, and the corpus, as well as synthesized demos, can be found on the project homepage.