{
  "fetched_at": "2026-10-19T06:31:57Z",
  "source_url": "https://www.kaggle.com/competitions/11785-hw-1-p-2-fall-2024-slack/data",
  "pages": [
    {
      "name": "data-description",
      "content": "train-clean-100: training set\ndev-clean folder: dev/validation set\ntest-clean folder: test set, sample_submission.csv",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "In this competition, you will create a multilayer perceptron for frame-level speech recognition. Specifically, you will create a frame-level phonetic transcription of raw Mel Frequency Cepstral Coefficients (MFCCs). The MLP will learn a feature representation and nonlinear classification boundary. To discriminate between each phoneme class label, cross-entropy loss will be used to minimize the dissimilarity between output logits and the target labels. The loss will be used during gradient descent to update the parameters of the neural network, thereby minimizing the cost function.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "Rules\n\nDon't cheat!\nApply yourself!\nHave fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "Speech recognition is an important field in deep learning with multiple applications. Speech is a fundamental\nform of human communication. Speech recognition involves converting spoken language into written text\nor data that could be understood by machines. Speech data refers to audio recordings of human speech,\nwhile phonemes represent the smallest units of sound that can convey a different meaning(bake, take: b,t).\nSpectrograms are visual representations of the acoustic properties of speech signals, i.e. captures the changes\nin the frequency over time.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Reference Model",
      "content": "Sparse Multilayer Perceptron for Phoneme Recognition\nNote: This Is provided as a conceptual reference paper only. It is very old, and the model in the paper performs poorly given our current methods and understanding. It is otherwise a nice paper, introducing the problem of phonetic transcript generation using multilayer perceptrons.\nLink: https://ieeexplore.ieee.org/document/5734801",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}