Experiment dataset supplementary materials for DLfM 2018 submission

This is the experiment dataset supplementary materials for the DLfM 2018 paper submission: An extended jingju solo singing voice dataset and its application on automatic assessment of singing pronunciation and overall quality at phoneme-level Files: dlfm_experiment_dataset_file_list.ods: recording file names of train, validation and test sets split. dlfm_experiment_dataset_phoneme_numbers.ods: phoneme numbers of each phone class in train, validation and test sets. freesound_extractor_feature_list.ods: freesoundExtractor feature name list used in ANOVA feature analysis. log-mel-scaler-keys-label-encoder.zip: files required for training the embedding model, includes logarithmic features, feature scaler, phoneme dictionary keys and label encoder. anova_analysis_essentia_feature.zip: Essentia freesoundExtractor features of each phoneme for ANOVA analysis. pretrained_embedding_models.zip: classification embedding models pretrained on the below datasets. The recordings listed in dlfm_experiment_dataset_file_list.ods are taken from a collection of jingju solo singing voice audio datasets, which contains three parts: Part 1: https://doi.org/10.5281/zenodo.780559 Part 2: https://doi.org/10.5281/zenodo.842229 Part 3: https://doi.org/10.5281/zenodo.1244732 Contact information: If you have any question, please contact the authors: Rong Gong: Email - rong<dot>gong<at>upf<dot>edu