File descriptions
Data files are available for download from this page.
File descriptions
train.npy - training features ;
train_labels.npy - training labels ;
dev.npy - development/validation features ;
dev_labels.npy - development/validation labels ;
test.npy - test features ;
sample.csv - sample submission in correct format ;
phonemes.txt - distinct phonemes
Feature Files
[train|dev|test].npy contain a numpy object array of shape [utterances]. Each utterance is a float32 ndarray of shape [time, frequency], where time is the length of the utterance. Frequency dimension is always 40 but time dimension is of variable length.
Label Files
[train|dev]_labels.npy contain a numpy object array of shape [utterances]. Each element in the array is an int32 array of shape [time] and provides the phoneme state label for each frame. There are 71 distinct labels [0-70], one for each subphoneme.