{
  "id": 121428,
  "title": "Is sound usefull?",
  "url": "/competitions/deepfake-detection-challenge/discussion/121428",
  "author_name": "",
  "post_date": "2019-12-13T08:56:17.990575900Z",
  "votes": 7,
  "comment_count": 6,
  "views": 0,
  "content": "<p>Is sound faked? if it is change to another persons voice - it is not distorted and it is impossible to distinguish fake/false?</p>",
  "messages": [
    {
      "id": "694159",
      "postDate": "12/13/2019 08:56:17",
      "content": "<p>Is sound faked? if it is change to another persons voice - it is not distorted and it is impossible to distinguish fake/false?</p>",
      "rawMarkdown": "Is sound faked? if it is change to another persons voice - it is not distorted and it is impossible to distinguish fake/false?",
      "votes": null
    },
    {
      "id": "694201",
      "postDate": "12/13/2019 09:44:34",
      "content": "<p>I can't find anything that explicitly says that audio was edited but it does say this in the intro, \"AI-generated videos of people doing <strong>and saying fictional</strong> things, have the potential to have a significant impact on how people determine the legitimacy of information presented online.\" </p>",
      "rawMarkdown": "I can't find anything that explicitly says that audio was edited but it does say this in the intro, \"AI-generated videos of people doing **and saying fictional** things, have the potential to have a significant impact on how people determine the legitimacy of information presented online.\"",
      "votes": null
    },
    {
      "id": "694202",
      "postDate": "12/13/2019 09:45:14",
      "content": "<p>It does seem that the voices have been altered, going by this <a href=\"https://www.kaggle.com/c/deepfake-detection-challenge/discussion/121179#latest-694133\">discussion</a></p>\n\n<p>So utilising the audio of the videos could be a nice approach.</p>",
      "rawMarkdown": "It does seem that the voices have been altered, going by this [discussion](https://www.kaggle.com/c/deepfake-detection-challenge/discussion/121179#latest-694133)\n\nSo utilising the audio of the videos could be a nice approach.",
      "votes": null
    },
    {
      "id": "694217",
      "postDate": "12/13/2019 10:01:20",
      "content": "<p>this is more about \"fake news\" not about \"deep fake\" :)</p>",
      "rawMarkdown": "this is more about \"fake news\" not about \"deep fake\" :)",
      "votes": null
    },
    {
      "id": "694249",
      "postDate": "12/13/2019 10:48:47",
      "content": "<blockquote>\n  <p>Identify videos with facial or voice manipulations</p>\n</blockquote>\n\n<p>this is about fake videos, not only faces... sound might be important.\nbtw, thank for the post, I didn't know that we also have to detect fake voices :)\nMore information abut the datset creation here: <a href=\"https://www.kaggle.com/c/deepfake-detection-challenge/discussion/121441#latest-694246\">DFDC: Insights about the Dataset creation, baselines...</a></p>",
      "rawMarkdown": "&gt; Identify videos with facial or voice manipulations\n\nthis is about fake videos, not only faces... sound might be important.\nbtw, thank for the post, I didn't know that we also have to detect fake voices :)\nMore information abut the datset creation here: [DFDC: Insights about the Dataset creation, baselines...](https://www.kaggle.com/c/deepfake-detection-challenge/discussion/121441#latest-694246)",
      "votes": null
    },
    {
      "id": "694439",
      "postDate": "12/13/2019 15:42:18",
      "content": "<p>Hmm, one of the videos was saying that PC's are better than mac's, how should I classify this ;)</p>",
      "rawMarkdown": "Hmm, one of the videos was saying that PC's are better than mac's, how should I classify this ;)",
      "votes": null
    },
    {
      "id": "694441",
      "postDate": "12/13/2019 15:47:58",
      "content": "<p>In the <a href=\"https://www.kaggle.com/c/deepfake-detection-challenge/data\">data description</a>:</p>\n\n<blockquote>\n  <p>What am I predicting?\n  You will be predicting whether or not a particular video is a deepfake. A deepfake could be either a face or voice swap (or both). In the training data, this is denoted by the string \"REAL\" or \"FAKE\" in the label column. In your submission, you will predict the probability that the video is a fake.</p>\n</blockquote>",
      "rawMarkdown": "In the [data description](https://www.kaggle.com/c/deepfake-detection-challenge/data):\n&gt; What am I predicting?\nYou will be predicting whether or not a particular video is a deepfake. A deepfake could be either a face or voice swap (or both). In the training data, this is denoted by the string \"REAL\" or \"FAKE\" in the label column. In your submission, you will predict the probability that the video is a fake.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 694201,
      "author_name": "gregoryeales",
      "author_url": "",
      "post_date": "12/13/2019 09:44:34",
      "content": "<p>I can't find anything that explicitly says that audio was edited but it does say this in the intro, \"AI-generated videos of people doing <strong>and saying fictional</strong> things, have the potential to have a significant impact on how people determine the legitimacy of information presented online.\" </p>",
      "votes": null,
      "replies": [
        {
          "id": 694217,
          "author_name": "jonasmatuzas",
          "author_url": "",
          "post_date": "12/13/2019 10:01:20",
          "content": "<p>this is more about \"fake news\" not about \"deep fake\" :)</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 694439,
          "author_name": "sdoria",
          "author_url": "",
          "post_date": "12/13/2019 15:42:18",
          "content": "<p>Hmm, one of the videos was saying that PC's are better than mac's, how should I classify this ;)</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 694441,
          "author_name": "arateris",
          "author_url": "",
          "post_date": "12/13/2019 15:47:58",
          "content": "<p>In the <a href=\"https://www.kaggle.com/c/deepfake-detection-challenge/data\">data description</a>:</p>\n\n<blockquote>\n  <p>What am I predicting?\n  You will be predicting whether or not a particular video is a deepfake. A deepfake could be either a face or voice swap (or both). In the training data, this is denoted by the string \"REAL\" or \"FAKE\" in the label column. In your submission, you will predict the probability that the video is a fake.</p>\n</blockquote>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 694202,
      "author_name": "leomuckley",
      "author_url": "",
      "post_date": "12/13/2019 09:45:14",
      "content": "<p>It does seem that the voices have been altered, going by this <a href=\"https://www.kaggle.com/c/deepfake-detection-challenge/discussion/121179#latest-694133\">discussion</a></p>\n\n<p>So utilising the audio of the videos could be a nice approach.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 694249,
      "author_name": "jesucristo",
      "author_url": "",
      "post_date": "12/13/2019 10:48:47",
      "content": "<blockquote>\n  <p>Identify videos with facial or voice manipulations</p>\n</blockquote>\n\n<p>this is about fake videos, not only faces... sound might be important.\nbtw, thank for the post, I didn't know that we also have to detect fake voices :)\nMore information abut the datset creation here: <a href=\"https://www.kaggle.com/c/deepfake-detection-challenge/discussion/121441#latest-694246\">DFDC: Insights about the Dataset creation, baselines...</a></p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "694159": "Is sound faked? if it is change to another persons voice - it is not distorted and it is impossible to distinguish fake/false?",
    "694201": "I can't find anything that explicitly says that audio was edited but it does say this in the intro, \"AI-generated videos of people doing **and saying fictional** things, have the potential to have a significant impact on how people determine the legitimacy of information presented online.\"",
    "694202": "It does seem that the voices have been altered, going by this [discussion](https://www.kaggle.com/c/deepfake-detection-challenge/discussion/121179#latest-694133)\n\nSo utilising the audio of the videos could be a nice approach.",
    "694217": "this is more about \"fake news\" not about \"deep fake\" :)",
    "694249": "&gt; Identify videos with facial or voice manipulations\n\nthis is about fake videos, not only faces... sound might be important.\nbtw, thank for the post, I didn't know that we also have to detect fake voices :)\nMore information abut the datset creation here: [DFDC: Insights about the Dataset creation, baselines...](https://www.kaggle.com/c/deepfake-detection-challenge/discussion/121441#latest-694246)",
    "694439": "Hmm, one of the videos was saying that PC's are better than mac's, how should I classify this ;)",
    "694441": "In the [data description](https://www.kaggle.com/c/deepfake-detection-challenge/data):\n&gt; What am I predicting?\nYou will be predicting whether or not a particular video is a deepfake. A deepfake could be either a face or voice swap (or both). In the training data, this is denoted by the string \"REAL\" or \"FAKE\" in the label column. In your submission, you will predict the probability that the video is a fake."
  },
  "source": "meta"
}