Calculates the RMS energy and related features.
Outputs
- RMS energy
- The root mean square energy of the signal.
- RMS energy delta
- The difference between the RMS energy of the current frame and the last.
- Moving average
- The Xth percentile of the RMS energy within a window.
- Dip probability
- The ratio of frames that have dipped below the dip threshold within the averaging window, where the threshold is a product of the moving average.
- Low energy ratio
- Percentage of frames in the file whose energy falls below a threshold, which is a product of the overall mean energy.
Parameters
- Use root
- Whether to apply the square root in RMS calculation. (default = 1)
- Moving average window size
- The size of the averaging window, in seconds. (default = 1.0)
- Moving average percentile
- The percentile used to calculate the average. (default = 3.0)
- Dip threshold
- The threshold for calculating the dip, which is multiplied by the moving average. (default = 3.0)
- Low energy threshold
- The threshold for calculating low energy, which is multiplied by the overall mean RMS energy (default = 1.0)
Description
RMS energy for each block is calculated as follows. The square root can be removed using the 'Use root' parameter (default = true)
\[ RMS = \sqrt{\displaystyle\sum\limits_{i=0}^n x_i^2} \]
The dip threshold is a simple but effective speech/music discriminator. It is defined as the ratio of frames in a moving window which fall below a threshold, where the threshold is a product of the moving average.
The low energy ratio is the percentage of blocks which fall below a certain RMS energy threshold. The threshold is set using the 'Low energy threshold' parameter which is a ratio of the overall mean RMS energy (default = 1).
