{
  "id": 307880,
  "title": "Augmentation line-up",
  "url": "/competitions/birdclef-2022/discussion/307880",
  "author_name": "",
  "post_date": "2022-02-16T03:24:51.954090700Z",
  "votes": 27,
  "comment_count": 3,
  "views": 0,
  "content": "<p>I  show you three <strong>augmentation methods</strong> that seem to be effective in this competition.</p>\n<ul>\n<li><p><a href=\"https://arxiv.org/abs/1904.08779\" target=\"_blank\">SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition</a>(2019)</p></li>\n<li><p><a href=\"https://arxiv.org/abs/2103.16858v3\" target=\"_blank\">SpecAugment++: A Hidden Space Data Augmentation Method for Acoustic Scene Classification</a>(2021)</p></li>\n<li><p><a href=\"https://arxiv.org/abs/2112.07156\" target=\"_blank\">ImportantAug: a data augmentation agent for speech</a>(2021)</p></li>\n</ul>",
  "messages": [
    {
      "id": "1692433",
      "postDate": "02/16/2022 03:24:51",
      "content": "<p>I  show you three <strong>augmentation methods</strong> that seem to be effective in this competition.</p>\n<ul>\n<li><p><a href=\"https://arxiv.org/abs/1904.08779\" target=\"_blank\">SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition</a>(2019)</p></li>\n<li><p><a href=\"https://arxiv.org/abs/2103.16858v3\" target=\"_blank\">SpecAugment++: A Hidden Space Data Augmentation Method for Acoustic Scene Classification</a>(2021)</p></li>\n<li><p><a href=\"https://arxiv.org/abs/2112.07156\" target=\"_blank\">ImportantAug: a data augmentation agent for speech</a>(2021)</p></li>\n</ul>",
      "rawMarkdown": "I  show you three **augmentation methods** that seem to be effective in this competition.\n\n- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://arxiv.org/abs/1904.08779)(2019)\n\n- [SpecAugment++: A Hidden Space Data Augmentation Method for Acoustic Scene Classification](https://arxiv.org/abs/2103.16858v3)(2021)\n\n- [ImportantAug: a data augmentation agent for speech](https://arxiv.org/abs/2112.07156)(2021)",
      "votes": null
    },
    {
      "id": "1692663",
      "postDate": "02/16/2022 07:02:19",
      "content": "<p>This is helpful, I will try to apply these techniques, thanks for sharing!!!</p>",
      "rawMarkdown": "This is helpful, I will try to apply these techniques, thanks for sharing!!!",
      "votes": null
    },
    {
      "id": "1784140",
      "postDate": "05/11/2022 00:47:34",
      "content": "<p>Very helpful information for audio beginners, thanks for sharing!</p>",
      "rawMarkdown": "Very helpful information for audio beginners, thanks for sharing!",
      "votes": null
    },
    {
      "id": "1797355",
      "postDate": "05/21/2022 22:21:37",
      "content": "<p>Thanks for sharing. Something tells me there should be something simpler =) <br>\nE.g. <a href=\"https://arxiv.org/abs/1807.06610\" target=\"_blank\">Learning Noise-Invariant Representations for Robust Speech Recognition</a>.  Although, this approach is also not so straightforward. </p>",
      "rawMarkdown": "Thanks for sharing. Something tells me there should be something simpler =) \nE.g. [Learning Noise-Invariant Representations for Robust Speech Recognition](https://arxiv.org/abs/1807.06610).  Although, this approach is also not so straightforward.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1692663,
      "author_name": "lallucycle",
      "author_url": "",
      "post_date": "02/16/2022 07:02:19",
      "content": "<p>This is helpful, I will try to apply these techniques, thanks for sharing!!!</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1784140,
      "author_name": "azamat25",
      "author_url": "",
      "post_date": "05/11/2022 00:47:34",
      "content": "<p>Very helpful information for audio beginners, thanks for sharing!</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1797355,
      "author_name": "budivoy",
      "author_url": "",
      "post_date": "05/21/2022 22:21:37",
      "content": "<p>Thanks for sharing. Something tells me there should be something simpler =) <br>\nE.g. <a href=\"https://arxiv.org/abs/1807.06610\" target=\"_blank\">Learning Noise-Invariant Representations for Robust Speech Recognition</a>.  Although, this approach is also not so straightforward. </p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1692433": "I  show you three **augmentation methods** that seem to be effective in this competition.\n\n- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://arxiv.org/abs/1904.08779)(2019)\n\n- [SpecAugment++: A Hidden Space Data Augmentation Method for Acoustic Scene Classification](https://arxiv.org/abs/2103.16858v3)(2021)\n\n- [ImportantAug: a data augmentation agent for speech](https://arxiv.org/abs/2112.07156)(2021)",
    "1692663": "This is helpful, I will try to apply these techniques, thanks for sharing!!!",
    "1784140": "Very helpful information for audio beginners, thanks for sharing!",
    "1797355": "Thanks for sharing. Something tells me there should be something simpler =) \nE.g. [Learning Noise-Invariant Representations for Robust Speech Recognition](https://arxiv.org/abs/1807.06610).  Although, this approach is also not so straightforward."
  },
  "source": "meta"
}