public Peking opera singing voice dataset
The dataset is manually labeled with the ArchiVoice Chinese system
The dataset's labels are generated via WFL and manually corrected.
The dataset is recorded at 16 bit 44.1k Hz in wav format and labeled in HTK label format (.lab).
Audio has been dereverbed and denoised for more even consistency.
The dataset is released with two versions, full length and segmented.
The full length dataset only includes wav and lab files, whereas the segmented dataset includes ds files and a transcription.csv for diffsinger usage.
The ds contains f0 and note slur data.
The dataset includes the following global phonemes: [exh,vf], exh for exhales and vf for vocal fry
Please do note that by no means is Jonathan professionally trained, and thus improper technique is to some point, to be expected.
See song list
Voice provided by Jonathan Huang 黃奕晨, owner of ArchiVoice, X/Twitter
ACV-003 © 2026 by YiChen Huang is licensed under CC BY-SA 4.0
The license only applies to direct use of the dataset and models mainly featuring the voice of ACV-003, and does not apply to models trained via parallel training.
Models trained using ACV-003 as supplementary data can follow its own license.