{
  "id": 95103,
  "title": "Please cite the paper describing this competition",
  "url": "/competitions/freesound-audio-tagging-2019/discussion/95103",
  "author_name": "Eduardo Fonseca",
  "post_date": "2019-06-10T02:52:49.215000",
  "votes": 0,
  "comment_count": 0,
  "views": 0,
  "content": "<p>Dear all, </p>\n\n<p>We have published the preprint of the paper describing this competition: task setup, the FSDKaggle2019 dataset, and the baseline system, so that participants can cite it when referring to details of this competition. It will be submitted to the DCASE2019 Workshop as a regular paper.</p>\n\n<p>If you are participating to this competition or using the FSDKaggle2019 dataset or baseline code, please cite the following paper:</p>\n\n<blockquote>\n  <p>Eduardo Fonseca, Manoj Plakal, Frederic Font, Daniel P. W. Ellis, and Xavier Serra. \"Audio tagging with noisy labels and minimal supervision\". Submitted to DCASE2019 Workshop, 2019. URL: <a href=\"https://arxiv.org/abs/1906.02975\">https://arxiv.org/abs/1906.02975</a></p>\n</blockquote>\n\n<p><strong>NOTE</strong>: the current manuscript is a draft where a few details of the dataset and evaluation results have been omitted purposefully until the DCASE2019Challenge has concluded. More information will be available in the official submission for the DCASE2019 Workshop. We will announce in this thread when the final paper version is available.</p>\n\n<p>You can also consider citing the Freesound Annotator, that was used to build the curated train set and test set of the FSDKaggle2019 dataset:</p>\n\n<blockquote>\n  <p>Eduardo Fonseca, Jordi Pons, Xavier Favory, Frederic Font, Dmitry Bogdanov, Andrés Ferraro, Sergio Oramas, Alastair Porter, and Xavier Serra. <a href=\"https://ismir2017.smcnus.org/wp-content/uploads/2017/10/161_Paper.pdf\">Freesound datasets: a platform for the creation of open audio datasets</a>. In Proceedings of the 18th International Society for Music Information Retrieval Conference (ISMIR 2017), pp 486-493. Suzhou, China, 2017.</p>\n</blockquote>\n\n<p>Thanks!</p>",
  "messages": [
    {
      "id": 548856,
      "postDate": "2019-06-10T02:52:49.217Z",
      "content": "<p>Dear all, </p>\n\n<p>We have published the preprint of the paper describing this competition: task setup, the FSDKaggle2019 dataset, and the baseline system, so that participants can cite it when referring to details of this competition. It will be submitted to the DCASE2019 Workshop as a regular paper.</p>\n\n<p>If you are participating to this competition or using the FSDKaggle2019 dataset or baseline code, please cite the following paper:</p>\n\n<blockquote>\n  <p>Eduardo Fonseca, Manoj Plakal, Frederic Font, Daniel P. W. Ellis, and Xavier Serra. \"Audio tagging with noisy labels and minimal supervision\". Submitted to DCASE2019 Workshop, 2019. URL: <a href=\"https://arxiv.org/abs/1906.02975\">https://arxiv.org/abs/1906.02975</a></p>\n</blockquote>\n\n<p><strong>NOTE</strong>: the current manuscript is a draft where a few details of the dataset and evaluation results have been omitted purposefully until the DCASE2019Challenge has concluded. More information will be available in the official submission for the DCASE2019 Workshop. We will announce in this thread when the final paper version is available.</p>\n\n<p>You can also consider citing the Freesound Annotator, that was used to build the curated train set and test set of the FSDKaggle2019 dataset:</p>\n\n<blockquote>\n  <p>Eduardo Fonseca, Jordi Pons, Xavier Favory, Frederic Font, Dmitry Bogdanov, Andrés Ferraro, Sergio Oramas, Alastair Porter, and Xavier Serra. <a href=\"https://ismir2017.smcnus.org/wp-content/uploads/2017/10/161_Paper.pdf\">Freesound datasets: a platform for the creation of open audio datasets</a>. In Proceedings of the 18th International Society for Music Information Retrieval Conference (ISMIR 2017), pp 486-493. Suzhou, China, 2017.</p>\n</blockquote>\n\n<p>Thanks!</p>",
      "rawMarkdown": "Dear all, \n\nWe have published the preprint of the paper describing this competition: task setup, the FSDKaggle2019 dataset, and the baseline system, so that participants can cite it when referring to details of this competition. It will be submitted to the DCASE2019 Workshop as a regular paper.\n\nIf you are participating to this competition or using the FSDKaggle2019 dataset or baseline code, please cite the following paper:\n\n&gt; Eduardo Fonseca, Manoj Plakal, Frederic Font, Daniel P. W. Ellis, and Xavier Serra. \"Audio tagging with noisy labels and minimal supervision\". Submitted to DCASE2019 Workshop, 2019. URL: [https://arxiv.org/abs/1906.02975](https://arxiv.org/abs/1906.02975)\n\n**NOTE**: the current manuscript is a draft where a few details of the dataset and evaluation results have been omitted purposefully until the DCASE2019Challenge has concluded. More information will be available in the official submission for the DCASE2019 Workshop. We will announce in this thread when the final paper version is available.\n\nYou can also consider citing the Freesound Annotator, that was used to build the curated train set and test set of the FSDKaggle2019 dataset:\n\n&gt; Eduardo Fonseca, Jordi Pons, Xavier Favory, Frederic Font, Dmitry Bogdanov, Andrés Ferraro, Sergio Oramas, Alastair Porter, and Xavier Serra. [Freesound datasets: a platform for the creation of open audio datasets](https://ismir2017.smcnus.org/wp-content/uploads/2017/10/161_Paper.pdf). In Proceedings of the 18th International Society for Music Information Retrieval Conference (ISMIR 2017), pp 486-493. Suzhou, China, 2017.\n\nThanks!"
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "548856": "Dear all, \n\nWe have published the preprint of the paper describing this competition: task setup, the FSDKaggle2019 dataset, and the baseline system, so that participants can cite it when referring to details of this competition. It will be submitted to the DCASE2019 Workshop as a regular paper.\n\nIf you are participating to this competition or using the FSDKaggle2019 dataset or baseline code, please cite the following paper:\n\n&gt; Eduardo Fonseca, Manoj Plakal, Frederic Font, Daniel P. W. Ellis, and Xavier Serra. \"Audio tagging with noisy labels and minimal supervision\". Submitted to DCASE2019 Workshop, 2019. URL: [https://arxiv.org/abs/1906.02975](https://arxiv.org/abs/1906.02975)\n\n**NOTE**: the current manuscript is a draft where a few details of the dataset and evaluation results have been omitted purposefully until the DCASE2019Challenge has concluded. More information will be available in the official submission for the DCASE2019 Workshop. We will announce in this thread when the final paper version is available.\n\nYou can also consider citing the Freesound Annotator, that was used to build the curated train set and test set of the FSDKaggle2019 dataset:\n\n&gt; Eduardo Fonseca, Jordi Pons, Xavier Favory, Frederic Font, Dmitry Bogdanov, Andrés Ferraro, Sergio Oramas, Alastair Porter, and Xavier Serra. [Freesound datasets: a platform for the creation of open audio datasets](https://ismir2017.smcnus.org/wp-content/uploads/2017/10/161_Paper.pdf). In Proceedings of the 18th International Society for Music Information Retrieval Conference (ISMIR 2017), pp 486-493. Suzhou, China, 2017.\n\nThanks!"
  }
}