Jingju a cappella singing pitch contour segmentation ground truth dataset
The dataset used in the paper:
Gong, Rong; Yang, Yile; Serra, Xavier; Pitch Contour Segmentation for Computer-aided Jingju Singing Training Sound and Music Computing (SMC 2016), 2016, Hamburg, Germany
is in "dataset" folder. The a cappella singing audio recordings are not contained in this folder due to their large size, please contact the paper authors to request them (firstname.lastname@example.org). In the "dataset" folder you can find:
Jinging singing scores in .xml format used for estimating the bigram note transition probabilities.
The ground truth annotation is used for:
melodic transcription (male_12_pos_1 missing)
evaluating the StdCdLe thresholding and the overall segmentation performance.
The subfolder "groundtruth" contains the following annotation for each jingju a cappella audio:
file name: description (format)
*_melodicTrans.csv: melodic transcription ground truth used for the evaluation (start_time pitch duration -).
*_coarseSeg.csv: StdCdLe ground truth used for the parameter optimization and the evaluation (segmentation points).
*_refinedSeg.csv: ground truth used for optimizing other parameters and the evaluation (start_time - duration).
*_pitchtrack.csv: pitch track (contour) extracted by pYIN pitch-tracking algorithm (filename time pitch).