# 11-785, Spring 2020, Homework 3 Part 2 — Data

来源：https://www.kaggle.com/competitions/11-785-s20-hw3p2/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

<h2>Data files</h2>
<p>Data files are available for download from this page.</p>
<h2>File descriptions</h2>
<ul>
<li><strong>wsj0_test.npy</strong> - test features</li>
<li><strong>wsj0_train.npy</strong> - train features</li>
<li><strong>wsj0_dev.npy</strong> - development/validation features</li>
<li><strong>wsj0_train_merged_labels.npy</strong> - training labels</li>
<li><strong>wsj0_dev_merged_labels.npy</strong> -  development/validation labels</li>
<li><strong>sample_submission.csv</strong> - sample submission in correct format. Submission is a single silence phoneme (".") for each utterance.</li>
<li><strong>phoneme_list.py</strong> - list of phoneme full names, and list of phoneme single-character encodings.</li>
</ul>
<h2>Feature Files</h2>
<p>Same data layout as previously.</p>
<h2>Label Files</h2>
<p>Array length is the number of utterances. Each item in the array is an array that is the length of the number of phonemes in that utterance. The labels are [0-45], 46 phonemes.</p>