0
$\begingroup$

Fft question: Do I need overlaps if I’m only grabbing some features like mel or bark? I don’t even necessarily need every frame of a STFT even one every second or so works. How I understand fft overlapping is that each overlap sums together after the final window after the inverse fft. However, for my needs I do not even do an inverse fft and I only extract mel and similar features in the frequency domain. So do I need to do overlapping for my use case? It doesn’t seem like the feature values i extract even consider the overlap.

Unless I’m supposed to combine overlapping fft values for the feature extraction itself??? Actually this makes me wonder if I should be doing that when extracting feature because some info is lost from the windowing to prevent spectral leaking. If that’s the case then do I just sum the window overlaps together after the fft and before feature extraction??

Because I don’t do that for spectral audio processing (again, i only sum after the final window after the ifft..) Thanks!

$\endgroup$
2
  • $\begingroup$ Hi! Welcome here! It's not clear to me what kind of features you're specifically trying to extract. Can you give me a definite list? and if you can, then these features are probably well-defined, and you need to do exactly what the (literature/wikipedia) definition says $\endgroup$ Oct 29, 2023 at 14:10
  • $\begingroup$ Thanks. That’s a good suggestion! I am extracting mel, bark, melcc, maybe a couple others I’m not decided fully. I think I will do an overlap , my main question now is if I sum the overlap immediately after the fft since I’m not doing an ifft $\endgroup$
    – Dillon B
    Oct 29, 2023 at 20:02

1 Answer 1

0
$\begingroup$

The most common way of doing an STFT is probably using a 50% overlap. The reason for this is quite simple: this roughly gives "equal" weight to all time domain samples and you are not missing anything important. Let's consider a signal that consists mainly out of a short large impulse: if you don't overlap you will get VERY different results depending how the impulse lines up with the window boundary.

If you signal is reasonably steady state and/or if the features you want to extract are not particularly sensitive to impulsive signals you can indeed do with less frames. However that depends a LOT on the property of your specific signals and the requirements of your application.

FWIW: Personally, I'm not a fan of not overlapping. Most "normal" audio signals do have prominent features that can be quite short and the incremental work of processing all samples using a 50% overlap seems minimal (for most applications).

$\endgroup$
1
  • $\begingroup$ Thanks for the response! I was thinking the same thing after asking. I guess my question now is when/how to correctly sum the overlaps for the feature analysis? Because usually when I do spectral processing it is on real time audio and I sum the overlaps after the window following the inverse fft. Since I am not doing an ifft and just getting features, would I sum the overlaps immediately after the fft before the feature analysis? Thanks!! $\endgroup$
    – Dillon B
    Oct 29, 2023 at 20:00

Your Answer

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

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