3
$\begingroup$

What is the difference between Short time energy(STE) or root mean square(RMS), Librosa library offers a function to calculate RMS but doesn't offer one to calculate STE, which gives the impression that STE isn't that useful and RMS is enough, While in researchers paper they use STE, so that I got confused a little bit.

What is the difference between them and can one behalf of the another ?

$\endgroup$
2
  • $\begingroup$ Personally, I am not familiar with the Short Time Energy metric so I would really appreciate it if you could share the formula to calculate it. Nevertheless, I am not really an expert on the field so I may be just missing something important. $\endgroup$
    – ZaellixA
    Mar 31 at 18:45
  • 1
    $\begingroup$ @ZaellixA en.wikipedia.org/wiki/Energy_(signal_processing) vlab.amrita.edu/… $\endgroup$
    – Ahmad
    Mar 31 at 19:17

1 Answer 1

2
$\begingroup$
  • RMS $$\sqrt{\frac{1}{N}\sum_{n_0}^{n_0+N}x^2[n]}$$
  • STE $$\sum_{n_0}^{n_0+N}x^2[n]$$

So there's little difference except the RMS is an average value, and the square root converts the values back to the original signal scale.

As far as why use one over the other, I'm guessing if you're using a short time window ($N$ small), then it might make more sense not to take the average... but that's really grasping at straws, especially if you consider the fact that some references define STE with the $1/N$ factor as well.

$\endgroup$
1
  • 1
    $\begingroup$ No, someone edited it. I've reverted it to my original answer. Sorry for the confusion ;) $\endgroup$
    – Jdip
    Apr 4 at 18:33

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Not the answer you're looking for? Browse other questions tagged or ask your own question.