Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis

By Yu Wang, Xinsheng Wang, Pengcheng Zhu, Jie Wu, Hanzhao Li, Heyang Xue, Yongmao Zhang, Lei Xie, Mengxiao Bi. 2022

147 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Rongjie Huang
2. Zhou Zhao
3. Jinglin Liu
4. Yi Ren
5. Dongchao Yang
6. Ziyue Jiang
7. Zhe Ye
8. Xuejiao Tan

In Signal Processing

1. Rongjie Huang
2. Zhou Zhao
3. Jinglin Liu
4. Yi Ren
5. Dongchao Yang
6. Ziyue Jiang
7. Xuejiao Tan
8. Zhenhui Ye

Citations in the corpus

• Make-A-Voice: Revisiting Voice Large Language Models as Scalable Multilingual and Multitask Learners (2024, positive): “We also use the female-singer OpenCPOP (Wang et al., 2022), multi-singer dataset OpenSinger (Huang et al., 2021), and M4Singer (Zhang et al., 2022a) as the singing voice data.”
• M4Singer: A Multi-Style, Multi-Singer and Musical Score Provided Mandarin Singing Corpus (2022, background): “Taking the Chinese SVS corpus as the focus, existing open resources suffer from either low quality [38], limited amount [26; 48], or lack of necessary musical score annotation [17].”
• NANSY++: Unified Voice Synthesis with Neural Analysis and Synthesis (2022, methodology): “2 EXPERIMENTS Experimental setup We trained the model using OpenCPOP dataset (Wang et al., 2022), a public singing dataset of 100 songs from a single female singer with aligned phoneme and MIDI-pitch sequence.”
• CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model (2023, methodology): “For the SVS task, we use the Opencpop dataset [Wang et al., 2022] containing 100 Chinese pop songs which are split into 3, 756 utterances with a total duration of around 5.”