{
  "id": 202523,
  "title": "Audio processing by using nnAudio",
  "url": "/competitions/rfcx-species-audio-detection/discussion/202523",
  "author_name": "",
  "post_date": "2020-12-10T14:44:27.949279Z",
  "votes": 5,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Hello</p>\n<p>Audio processing by using pytorch 1D convolution network. By doing so, spectrograms can be generated from audio on-the-fly during neural network training. Kapre and torch-stft have a similar concept in which they also use 1D convolution from keras adn PyTorch to do the waveforms to spectrogram conversions.</p>\n<p>Maybe it can help you for the improvement of your kernel<br>\n<a href=\"https://www.kaggle.com/mekhdigakhramanian/audio-processing-by-using-nnaudio/\" target=\"_blank\">https://www.kaggle.com/mekhdigakhramanian/audio-processing-by-using-nnaudio/</a></p>",
  "messages": [
    {
      "id": "1108324",
      "postDate": "12/10/2020 14:44:27",
      "content": "<p>Hello</p>\n<p>Audio processing by using pytorch 1D convolution network. By doing so, spectrograms can be generated from audio on-the-fly during neural network training. Kapre and torch-stft have a similar concept in which they also use 1D convolution from keras adn PyTorch to do the waveforms to spectrogram conversions.</p>\n<p>Maybe it can help you for the improvement of your kernel<br>\n<a href=\"https://www.kaggle.com/mekhdigakhramanian/audio-processing-by-using-nnaudio/\" target=\"_blank\">https://www.kaggle.com/mekhdigakhramanian/audio-processing-by-using-nnaudio/</a></p>",
      "rawMarkdown": "Hello\n\nAudio processing by using pytorch 1D convolution network. By doing so, spectrograms can be generated from audio on-the-fly during neural network training. Kapre and torch-stft have a similar concept in which they also use 1D convolution from keras adn PyTorch to do the waveforms to spectrogram conversions.\n\nMaybe it can help you for the improvement of your kernel\nhttps://www.kaggle.com/mekhdigakhramanian/audio-processing-by-using-nnaudio/",
      "votes": null
    },
    {
      "id": "1108359",
      "postDate": "12/10/2020 15:16:30",
      "content": "<p>Thank you, very useful topic</p>",
      "rawMarkdown": "Thank you, very useful topic",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1108359,
      "author_name": "michaelhunter",
      "author_url": "",
      "post_date": "12/10/2020 15:16:30",
      "content": "<p>Thank you, very useful topic</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1108324": "Hello\n\nAudio processing by using pytorch 1D convolution network. By doing so, spectrograms can be generated from audio on-the-fly during neural network training. Kapre and torch-stft have a similar concept in which they also use 1D convolution from keras adn PyTorch to do the waveforms to spectrogram conversions.\n\nMaybe it can help you for the improvement of your kernel\nhttps://www.kaggle.com/mekhdigakhramanian/audio-processing-by-using-nnaudio/",
    "1108359": "Thank you, very useful topic"
  },
  "source": "meta"
}