{
  "fetched_at": "2026-10-20T08:47:03Z",
  "source_url": "https://www.kaggle.com/competitions/11785-summer2021-hw3p2/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<p>\nSee this link for data download: <a href=\"https://www.kaggle.com/c/11785-spring2021-hw3p2/data\">https://www.kaggle.com/c/11785-spring2021-hw3p2/data</a>\n</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p>The feature data of this homework are the same as homework 1 part 2. There are many variable length utterances comprised of 40 dimensional timesteps. You can use recurrent layers and their variants. You may also use convolutional layers if you so choose.\n</p>\n<p>\nYour task will be to take the sequence of features and map them to a sequence of phonemes. Keep in mind the number of phonemes will not equal the number of timesteps. Refer to the write-up for more information.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The evaluation metric will be the Levenshtein distance (character level minimum edit distance) from the ground truth. The labels will have the sequence of phonemes, but not the alignment. To handle this CTC Loss will be used during training and a search should be used on the output distribution for prediction. More information is provided in the writeup.</p>\n<pre>id,label<br>0,.N pHhEk fYszSiH.<br></pre>",
      "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
    }
  ]
}