{
  "id": 49427,
  "title": "Classifying audio using One Dimensional Convolutional layers",
  "url": "/competitions/tensorflow-speech-recognition-challenge/discussion/49427",
  "author_name": "",
  "post_date": "2018-02-11T06:55:53.586968500Z",
  "votes": null,
  "comment_count": 2,
  "views": 0,
  "content": "<p>AudioNet - Speech classification using One dimensional convolutions for feature extraction</p>\n\n<p>Codes and description are available in <a href=\"https://github.com/vj-1988/AudioNet-V1\">Github link</a></p>",
  "messages": [
    {
      "id": "280836",
      "postDate": "02/11/2018 06:55:53",
      "content": "<p>AudioNet - Speech classification using One dimensional convolutions for feature extraction</p>\n\n<p>Codes and description are available in <a href=\"https://github.com/vj-1988/AudioNet-V1\">Github link</a></p>",
      "rawMarkdown": "AudioNet - Speech classification using One dimensional convolutions for feature extraction\n\nCodes and description are available in [Github link][1]\n\n\n  [1]: https://github.com/vj-1988/AudioNet-V1",
      "votes": null
    },
    {
      "id": "280854",
      "postDate": "02/11/2018 07:35:01",
      "content": "<p>Thank you for sharing your model.</p>\n\n<p>Can you show the public and private LB score with the model? </p>",
      "rawMarkdown": "Thank you for sharing your model.\n\nCan you show the public and private LB score with the model?",
      "votes": null
    },
    {
      "id": "281272",
      "postDate": "02/12/2018 11:52:39",
      "content": "<p>I remember getting accuracy of 80.1 and 79.3 in private and public score. I haven't submitted them yet since I am also experimenting with deeper architectures.</p>",
      "rawMarkdown": "I remember getting accuracy of 80.1 and 79.3 in private and public score. I haven't submitted them yet since I am also experimenting with deeper architectures.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 280854,
      "author_name": "yatzhash",
      "author_url": "",
      "post_date": "02/11/2018 07:35:01",
      "content": "<p>Thank you for sharing your model.</p>\n\n<p>Can you show the public and private LB score with the model? </p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 281272,
      "author_name": "hoticevijay",
      "author_url": "",
      "post_date": "02/12/2018 11:52:39",
      "content": "<p>I remember getting accuracy of 80.1 and 79.3 in private and public score. I haven't submitted them yet since I am also experimenting with deeper architectures.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "280836": "AudioNet - Speech classification using One dimensional convolutions for feature extraction\n\nCodes and description are available in [Github link][1]\n\n\n  [1]: https://github.com/vj-1988/AudioNet-V1",
    "280854": "Thank you for sharing your model.\n\nCan you show the public and private LB score with the model?",
    "281272": "I remember getting accuracy of 80.1 and 79.3 in private and public score. I haven't submitted them yet since I am also experimenting with deeper architectures."
  },
  "source": "meta"
}