{
  "fetched_at": "2026-10-19T06:34:16Z",
  "source_url": "https://www.kaggle.com/competitions/11-785-fall-20-homework-3-slack/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<h2>Data files</h2>\n<p>Data files are available for download from this page.</p>\n<h2>File descriptions</h2>\n<ul>\n<li><strong>test.npy</strong> - test features</li>\n<li><strong>train.npy</strong> - train features</li>\n<li><strong>dev.npy</strong> - development/validation features</li>\n<li><strong>train_labels.npy</strong> - training labels</li>\n<li><strong>dev_labels.npy</strong> -  development/validation labels</li>\n<li><strong>sample_submission.csv</strong> - sample submission in correct format. Submission is a single silence phoneme (\".\") for each utterance.</li>\n<li><strong>phoneme_list.py</strong> - list of phoneme full names, and list of phoneme single-character encodings.</li>\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<h2>HW3P2</h2>\n\n<p>This is the Kaggle competition for hw3p2. The dataset will be used for this contest. We are going to be using unaligned labels in this contest. That means you are given the list of phonemes for each utterance, but not which frames correspond to which phonemes. Inference of the alignment will require using CTC loss.</p>\n Read about Levenshtein Distance [here](https://en.wikipedia.org/wiki/Levenshtein_distance) \n<h2>What does the data look like?</h2>\n<p>Input data is an array of utterances, each of which is shaped (frames, frequencies). Labels are simply the list of phonemes in the utterance [0-40]. There are 41 phoneme labels. The phoneme array will be as long as however many phonemes are in the utterance. We provide a lookup mapping each phoneme to a single character for the purposes of this competition. \n\n</p><h2>The Task</h2>\n\n<p>Predict the phonemes contained in utterances in the test set. You are not given aligned phonemes in the training data, and you are not asked to produce alignment for the test data.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<h2>Evaluation Metric</h2>\n\n<p>You will be evaluated using Kaggle's character-level string edit distance. Since we mapped each phoneme to a single character, that means you are being evaluated on phoneme edit distance.\n\nWe are using Levenshtein distance, which counts how many additions deletions and modifications are required to make one sequence into another..</p>\n Read about Levenshtein Distance [here](https://en.wikipedia.org/wiki/Levenshtein_distance) \n<h2>Submission Format</h2>\n<p>Your submission should be a CSV file. The headers should be \"Id\", and \"Predicted\". - Id refers to the 0-based index of utterance in the test set - Predicted is the phoneme string. See the sample submission for more details.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}