{
  "fetched_at": "2026-10-19T08:51:41Z",
  "source_url": "https://www.kaggle.com/competitions/104-1-mlds-hw3/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<p>The data is exactly the same as in homework 1 except we add one file 'phones/48_idx_chr.map' which provides the mapping from 48 phoneme to the corresponding index and English character. You may download the file '48_idx_chr.map' directly if you already have the training data in homework 1.</p>\r\n<p>Also, we provide you the posterior gram of both testing and training set after a trained DNN. If you didn't get good result in homework 1, then you may try to train you RNN with this given posterior gram.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p><strong>1. Introduction</strong></p>\r\n<p>In this homework, you are going to implement Structured SVM as a more general purpose decoder. In homework 1, we only consider frame to phone label probabilities. In homework 3, we use Structured SVM to model the phone transition probabilities, and see the whole utterance as one training data, instead of frame by frame training. Note this is different from homework 1 where homework 1 is a classification problem (output phone label), homework 3 is structure learning problem (output phone label sequence).</p>\r\n<p><strong>2. Problem Description</strong></p>\r\n<p><strong>Goal</strong>: Given input feature of each time frame, utilizes structured SVM to predict the whole utterance.</p>\r\n<p><strong>Input</strong>: The raw wave files, the MFCC features, the FBANK features or any other derivations. (Exactly the same as homework 1)</p>\r\n<p><strong>Output</strong>: 39 phone label sequence.</p>\r\n<p>Firstly, the output label sequence is mapped to 39 phone labels (replace by a-z and A-M 39 English characters). Secondly, it should reduce replicated phones. Thirdly, the front end and back end silence is removed from the label sequence. Details descriptions are in the <a href=\"https://docs.google.com/presentation/d/1sXXfcODQ_jkDaxPDRyqpZ7ELBscnFlgV9Kl0qdrk9BA/edit?usp=sharing\">sildes</a>.</p>\r\n<p><strong>3. Implementation</strong></p>\r\n<p>You can use any methods with structured learning algorithm, e.g., HMM, structured SVM, CRF. You are encouraged to use any result or model from homework 1. Any other toolkit or library is required to ask TA for sure.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The performance is measured by <a href=\"http://en.wikipedia.org/wiki/Levenshtein_distance\">Levenshtein distance</a>(a.k.a. Edit distance). (The lower the better).</p>\r\n<p><strong>Note</strong></p>\r\n<p>You should transform your phone sequence into a character string without space, where each character is one phone label. The encoding is mapping from phone to English character is provided in the attachments.</p>\r\n<h1>Submission Format</h1>\r\n<p>Submission files should contain two columns: id and phone_sequence.</p>\r\n<p>id is the utterance name (eg. fadg0_si1279)</p>\r\n<p>phone_sequence is the corresponding trimmed phone sequence (eg. HrLAJarDeBLMrDcLMwU).</p>\r\n<p>The file should contain a header and have the following format:</p>\r\n<pre>id,phone_sequence<br />fadg0_si1279,HrLAJarDeBLMrDcLMwU<br />fadg0_si1909,vbLAFKnLhyUwJmrBJLAwLSyLAwKr<br />fadg0_si649,lwLJctryJvrCaBgLHwDLKyDwLHJywDLHrLHwJnDryJLAbLMtrBwLABsmrQKn<br />fadg0_sx109,SJKyJBnLMwDJLHIyDyCrFLABSaDwDJLMyLAJBc<br />...</pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "\r\n\t<!-- Begin Base Rules -->\r\n    <h3>One account per participant</h3>\r\n    <p>You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.</p>\r\n    <h3>No private sharing outside teams</h3>\r\n    <p>\r\n        Privately sharing code or data outside of teams is not permitted.\r\n        It's okay to share code if made available to all participants on the forums.\r\n    </p>\r\n    <h3>Team Mergers</h3>\r\n    <p>\r\n        Team mergers are allowed and can be performed by the team leader. In order to merge, the combined team must have a total submission count less than or equal to the maximum allowed as of the merge date. The maximum allowed is the number of submissions per day multiplied by the number of days the competition has been running.<br/>\r\n    </p>\r\n\r\n    <h3>Team Limits</h3>\r\n    <p>There is no maximum team size.</p>\r\n    <h3>Submission Limits</h3>\r\n    <p>You may submit a maximum of 10 entries per day.</p>\r\n    <p>You may select up to 2 final submissions for judging.</p>\r\n    <h3>Competition Timeline</h3>\r\n    <p>Start Date: <strong>11/16/2015 6:46 PM UTC</strong></p>\r\n    <p>Merger Deadline: <strong>None</strong></p>\r\n    <p>Entry Deadline: <strong>None</strong></p>\r\n    <p>End Date: <strong>12/7/2015 6:00 AM UTC</strong></p>\r\n\t<!-- End Base Rules -->\r\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}