{
  "id": 307881,
  "title": "Sound separation paper",
  "url": "/competitions/birdclef-2022/discussion/307881",
  "author_name": "",
  "post_date": "2022-02-16T03:25:14.076105Z",
  "votes": 18,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Recently, an interesting paper was published by Google Research.</p>\n<p><a href=\"https://arxiv.org/abs/2110.03209\" target=\"_blank\">Improving Bird Classification with Unsupervised Sound Separation</a></p>\n<p><img src=\"https://user-images.githubusercontent.com/34497776/154173940-60f14b8d-9c06-4678-a3b5-25aad39defa6.png\" alt=\"image\"></p>\n<blockquote>\n  <p>Figure taken from the paper.</p>\n</blockquote>\n<p>In this paper, they presented some <strong>impressive techniques.</strong></p>\n<ul>\n<li><p><a href=\"http://www.justinsalamon.com/uploads/4/3/9/4/4394963/mcfee_autopool_taslp_2018.pdf\" target=\"_blank\">autopooling</a><br>\ngithub : <a href=\"https://github.com/marl/autopool\" target=\"_blank\">https://github.com/marl/autopool</a></p></li>\n<li><p><a href=\"https://arxiv.org/abs/1607.05666\" target=\"_blank\">PCEN mel-spec</a><br>\ngithub(pytorch) : <a href=\"https://github.com/daemon/pytorch-pcen\" target=\"_blank\">https://github.com/daemon/pytorch-pcen</a></p></li>\n</ul>\n<p>These techniques may be useful in this competition.</p>",
  "messages": [
    {
      "id": "1692434",
      "postDate": "02/16/2022 03:25:14",
      "content": "<p>Recently, an interesting paper was published by Google Research.</p>\n<p><a href=\"https://arxiv.org/abs/2110.03209\" target=\"_blank\">Improving Bird Classification with Unsupervised Sound Separation</a></p>\n<p><img src=\"https://user-images.githubusercontent.com/34497776/154173940-60f14b8d-9c06-4678-a3b5-25aad39defa6.png\" alt=\"image\"></p>\n<blockquote>\n  <p>Figure taken from the paper.</p>\n</blockquote>\n<p>In this paper, they presented some <strong>impressive techniques.</strong></p>\n<ul>\n<li><p><a href=\"http://www.justinsalamon.com/uploads/4/3/9/4/4394963/mcfee_autopool_taslp_2018.pdf\" target=\"_blank\">autopooling</a><br>\ngithub : <a href=\"https://github.com/marl/autopool\" target=\"_blank\">https://github.com/marl/autopool</a></p></li>\n<li><p><a href=\"https://arxiv.org/abs/1607.05666\" target=\"_blank\">PCEN mel-spec</a><br>\ngithub(pytorch) : <a href=\"https://github.com/daemon/pytorch-pcen\" target=\"_blank\">https://github.com/daemon/pytorch-pcen</a></p></li>\n</ul>\n<p>These techniques may be useful in this competition.</p>",
      "rawMarkdown": "Recently, an interesting paper was published by Google Research.\n\n[Improving Bird Classification with Unsupervised Sound Separation](https://arxiv.org/abs/2110.03209)\n\n![image](https://user-images.githubusercontent.com/34497776/154173940-60f14b8d-9c06-4678-a3b5-25aad39defa6.png)\n> Figure taken from the paper.\n\nIn this paper, they presented some **impressive techniques.**\n\n- [autopooling](http://www.justinsalamon.com/uploads/4/3/9/4/4394963/mcfee_autopool_taslp_2018.pdf)\ngithub : https://github.com/marl/autopool\n\n- [PCEN mel-spec](https://arxiv.org/abs/1607.05666)\ngithub(pytorch) : https://github.com/daemon/pytorch-pcen\n\nThese techniques may be useful in this competition.",
      "votes": null
    },
    {
      "id": "1692662",
      "postDate": "02/16/2022 07:01:22",
      "content": "<p>Nice, Thanks for sharing, but no matter how well you do, you will not get upvotes unless you have your own bot army!!!</p>",
      "rawMarkdown": "Nice, Thanks for sharing, but no matter how well you do, you will not get upvotes unless you have your own bot army!!!",
      "votes": null
    },
    {
      "id": "1744414",
      "postDate": "04/04/2022 00:50:15",
      "content": "<p>Hi there, I tried leveraging this technique and created a notebook to showcase it. Check it out if you'd like! Thanks for putting me on to it :)</p>\n<p><a href=\"https://www.kaggle.com/code/dschettler8845/birdclef-22-sound-separation-experiment?scriptVersionId=92029448\" target=\"_blank\">https://www.kaggle.com/code/dschettler8845/birdclef-22-sound-separation-experiment?scriptVersionId=92029448</a></p>",
      "rawMarkdown": "Hi there, I tried leveraging this technique and created a notebook to showcase it. Check it out if you'd like! Thanks for putting me on to it :)\n\nhttps://www.kaggle.com/code/dschettler8845/birdclef-22-sound-separation-experiment?scriptVersionId=92029448",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1692662,
      "author_name": "lallucycle",
      "author_url": "",
      "post_date": "02/16/2022 07:01:22",
      "content": "<p>Nice, Thanks for sharing, but no matter how well you do, you will not get upvotes unless you have your own bot army!!!</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1744414,
      "author_name": "dschettler8845",
      "author_url": "",
      "post_date": "04/04/2022 00:50:15",
      "content": "<p>Hi there, I tried leveraging this technique and created a notebook to showcase it. Check it out if you'd like! Thanks for putting me on to it :)</p>\n<p><a href=\"https://www.kaggle.com/code/dschettler8845/birdclef-22-sound-separation-experiment?scriptVersionId=92029448\" target=\"_blank\">https://www.kaggle.com/code/dschettler8845/birdclef-22-sound-separation-experiment?scriptVersionId=92029448</a></p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1692434": "Recently, an interesting paper was published by Google Research.\n\n[Improving Bird Classification with Unsupervised Sound Separation](https://arxiv.org/abs/2110.03209)\n\n![image](https://user-images.githubusercontent.com/34497776/154173940-60f14b8d-9c06-4678-a3b5-25aad39defa6.png)\n> Figure taken from the paper.\n\nIn this paper, they presented some **impressive techniques.**\n\n- [autopooling](http://www.justinsalamon.com/uploads/4/3/9/4/4394963/mcfee_autopool_taslp_2018.pdf)\ngithub : https://github.com/marl/autopool\n\n- [PCEN mel-spec](https://arxiv.org/abs/1607.05666)\ngithub(pytorch) : https://github.com/daemon/pytorch-pcen\n\nThese techniques may be useful in this competition.",
    "1692662": "Nice, Thanks for sharing, but no matter how well you do, you will not get upvotes unless you have your own bot army!!!",
    "1744414": "Hi there, I tried leveraging this technique and created a notebook to showcase it. Check it out if you'd like! Thanks for putting me on to it :)\n\nhttps://www.kaggle.com/code/dschettler8845/birdclef-22-sound-separation-experiment?scriptVersionId=92029448"
  },
  "source": "meta"
}