{
  "id": 160802,
  "title": "Useful features available from the audio analysis",
  "url": "/competitions/birdsong-recognition/discussion/160802",
  "author_name": "",
  "post_date": "2020-06-22T18:03:11.210850600Z",
  "votes": 3,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Hi folks,</p>\n\n<p>It's my first audio classification competition on Kaggle so can anyone share a brief idea about the features (domain/problem specific) that can be used apart from the ones mentioned in some kernels. Thank you.</p>\n\n<p>Happy Kaggling!</p>",
  "messages": [
    {
      "id": "897234",
      "postDate": "06/22/2020 18:03:11",
      "content": "<p>Hi folks,</p>\n\n<p>It's my first audio classification competition on Kaggle so can anyone share a brief idea about the features (domain/problem specific) that can be used apart from the ones mentioned in some kernels. Thank you.</p>\n\n<p>Happy Kaggling!</p>",
      "rawMarkdown": "Hi folks,\n\nIt's my first audio classification competition on Kaggle so can anyone share a brief idea about the features (domain/problem specific) that can be used apart from the ones mentioned in some kernels. Thank you.\n\nHappy Kaggling!",
      "votes": null
    },
    {
      "id": "914280",
      "postDate": "07/03/2020 18:11:39",
      "content": "<p>Frame Energy\n            In this we find the RSME of the signal and save it to CSV file to analyze.\n Frame Intensity / Loudness:\nSpectrograms:\n spectrogram is a visual representation of the spectrum of frequencies of a signal as it varies with time.\nChromagrams\nFourier Transform:\nIt transforms our time-domain signal into the frequency domain. Whereas the time domain expresses our signal as a sequence of samples, the frequency domain expresses our signal as a superposition of sinusoids of varying magnitudes, frequencies, and phase offsets.\nShort-Term Energy\nIt is the mean squared value of the waveform values in the data frame and represents the temporal envelope of the signal. \nZero-Crossing Rate\nThe zero-crossing rate is the rate of sign-changes along a signal, i.e., the rate at which the signal changes from positive to zero to negative or from negative to zero to positive.\n Short-Term Entropy of Energy\n Spectral Centroid:\nThe spectral centroid is a measure used in digital signal processing to characterise a spectrum. It indicates where the center of mass of the spectrum is located. Perceptually, it has a robust connection with the impression of brightness of a sound.\nSpectral Flux:\nA high value of spectral flux indicates a sudden change in spectral magnitudes and therefore a possible segment boundary at the r th frame.\nF0 Harmonics ratios:\nIt is computed by measuring the periodicity of the time-domain waveform.\nIt may also be estimated from the signal spectrum as the frequency of the first harmonic or as the spacing between harmonics of the periodic signal.\nMel-/Bark-Frequency-Cepstral Coefficients (MFCC) :\nMFCC are perceptually motivated features that provide a compact representation of the short-time spectrum envelope. \nSpectral Roll-Off Frequency:\nSpectral rolloff is the frequency below which a specified percentage of the total spectral energy, e.g. 85%, lies.</p>",
      "rawMarkdown": "Frame Energy\n            In this we find the RSME of the signal and save it to CSV file to analyze.\n Frame Intensity / Loudness:\nSpectrograms:\n spectrogram is a visual representation of the spectrum of frequencies of a signal as it varies with time.\nChromagrams\nFourier Transform:\nIt transforms our time-domain signal into the frequency domain. Whereas the time domain expresses our signal as a sequence of samples, the frequency domain expresses our signal as a superposition of sinusoids of varying magnitudes, frequencies, and phase offsets.\nShort-Term Energy\nIt is the mean squared value of the waveform values in the data frame and represents the temporal envelope of the signal. \nZero-Crossing Rate\nThe zero-crossing rate is the rate of sign-changes along a signal, i.e., the rate at which the signal changes from positive to zero to negative or from negative to zero to positive.\n Short-Term Entropy of Energy\n Spectral Centroid:\nThe spectral centroid is a measure used in digital signal processing to characterise a spectrum. It indicates where the center of mass of the spectrum is located. Perceptually, it has a robust connection with the impression of brightness of a sound.\nSpectral Flux:\nA high value of spectral flux indicates a sudden change in spectral magnitudes and therefore a possible segment boundary at the r th frame.\nF0 Harmonics ratios:\nIt is computed by measuring the periodicity of the time-domain waveform.\nIt may also be estimated from the signal spectrum as the frequency of the first harmonic or as the spacing between harmonics of the periodic signal.\nMel-/Bark-Frequency-Cepstral Coefficients (MFCC) :\nMFCC are perceptually motivated features that provide a compact representation of the short-time spectrum envelope. \nSpectral Roll-Off Frequency:\nSpectral rolloff is the frequency below which a specified percentage of the total spectral energy, e.g. 85%, lies.",
      "votes": null
    },
    {
      "id": "914960",
      "postDate": "07/04/2020 11:42:10",
      "content": "<p>Thanks a lot for the detailed description Ashwani. These are very useful features.</p>",
      "rawMarkdown": "Thanks a lot for the detailed description Ashwani. These are very useful features.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 914280,
      "author_name": "ashkhagan",
      "author_url": "",
      "post_date": "07/03/2020 18:11:39",
      "content": "<p>Frame Energy\n            In this we find the RSME of the signal and save it to CSV file to analyze.\n Frame Intensity / Loudness:\nSpectrograms:\n spectrogram is a visual representation of the spectrum of frequencies of a signal as it varies with time.\nChromagrams\nFourier Transform:\nIt transforms our time-domain signal into the frequency domain. Whereas the time domain expresses our signal as a sequence of samples, the frequency domain expresses our signal as a superposition of sinusoids of varying magnitudes, frequencies, and phase offsets.\nShort-Term Energy\nIt is the mean squared value of the waveform values in the data frame and represents the temporal envelope of the signal. \nZero-Crossing Rate\nThe zero-crossing rate is the rate of sign-changes along a signal, i.e., the rate at which the signal changes from positive to zero to negative or from negative to zero to positive.\n Short-Term Entropy of Energy\n Spectral Centroid:\nThe spectral centroid is a measure used in digital signal processing to characterise a spectrum. It indicates where the center of mass of the spectrum is located. Perceptually, it has a robust connection with the impression of brightness of a sound.\nSpectral Flux:\nA high value of spectral flux indicates a sudden change in spectral magnitudes and therefore a possible segment boundary at the r th frame.\nF0 Harmonics ratios:\nIt is computed by measuring the periodicity of the time-domain waveform.\nIt may also be estimated from the signal spectrum as the frequency of the first harmonic or as the spacing between harmonics of the periodic signal.\nMel-/Bark-Frequency-Cepstral Coefficients (MFCC) :\nMFCC are perceptually motivated features that provide a compact representation of the short-time spectrum envelope. \nSpectral Roll-Off Frequency:\nSpectral rolloff is the frequency below which a specified percentage of the total spectral energy, e.g. 85%, lies.</p>",
      "votes": null,
      "replies": [
        {
          "id": 914960,
          "author_name": "ishaan45",
          "author_url": "",
          "post_date": "07/04/2020 11:42:10",
          "content": "<p>Thanks a lot for the detailed description Ashwani. These are very useful features.</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "897234": "Hi folks,\n\nIt's my first audio classification competition on Kaggle so can anyone share a brief idea about the features (domain/problem specific) that can be used apart from the ones mentioned in some kernels. Thank you.\n\nHappy Kaggling!",
    "914280": "Frame Energy\n            In this we find the RSME of the signal and save it to CSV file to analyze.\n Frame Intensity / Loudness:\nSpectrograms:\n spectrogram is a visual representation of the spectrum of frequencies of a signal as it varies with time.\nChromagrams\nFourier Transform:\nIt transforms our time-domain signal into the frequency domain. Whereas the time domain expresses our signal as a sequence of samples, the frequency domain expresses our signal as a superposition of sinusoids of varying magnitudes, frequencies, and phase offsets.\nShort-Term Energy\nIt is the mean squared value of the waveform values in the data frame and represents the temporal envelope of the signal. \nZero-Crossing Rate\nThe zero-crossing rate is the rate of sign-changes along a signal, i.e., the rate at which the signal changes from positive to zero to negative or from negative to zero to positive.\n Short-Term Entropy of Energy\n Spectral Centroid:\nThe spectral centroid is a measure used in digital signal processing to characterise a spectrum. It indicates where the center of mass of the spectrum is located. Perceptually, it has a robust connection with the impression of brightness of a sound.\nSpectral Flux:\nA high value of spectral flux indicates a sudden change in spectral magnitudes and therefore a possible segment boundary at the r th frame.\nF0 Harmonics ratios:\nIt is computed by measuring the periodicity of the time-domain waveform.\nIt may also be estimated from the signal spectrum as the frequency of the first harmonic or as the spacing between harmonics of the periodic signal.\nMel-/Bark-Frequency-Cepstral Coefficients (MFCC) :\nMFCC are perceptually motivated features that provide a compact representation of the short-time spectrum envelope. \nSpectral Roll-Off Frequency:\nSpectral rolloff is the frequency below which a specified percentage of the total spectral energy, e.g. 85%, lies.",
    "914960": "Thanks a lot for the detailed description Ashwani. These are very useful features."
  },
  "source": "meta"
}