This corpus consists of 100 unique Mandarin songs, which were recorded by a professional female singer. All audio files were recorded with studio-quality at a sampling rate of 44,100 Hz in a professional recording studio environment.
All singing recordings have been phonetically annotated with utterance/note/phoneme boundaries and pitch types. The final dataset contains 3,756 utterances, with a total of about 5.2 hours. The testing set consists of 5 randomly chosen songs, and baseline synthesized results are provided.
The Opencpop dataset is available to download for non-commercial purposes under a CC BY-NC-ND 4.0 License.