# 11-785, Spring 2020, H1P2 - Slack — Data

来源：https://www.kaggle.com/competitions/11785-spring2020-hw1p2-slack2/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

<h1>File descriptions</h1>
Data files are available for download from this page.

<h2>File descriptions</h2>
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_submission.csv - sample submission in correct format
<h2>Feature Files</h2>
[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.

<h2>Label Files</h2>
[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 138 distinct labels [0-137], one for each subphoneme.