I have created a little classifier that listens for certain keywords. Sometimes it will not react to a keyword, but if I shout the word, then the classifier will be able to pick it up.

The classifier uses MFCC as features, which is basically a Short-time Fourier Transform with some extra stuff. This tells me that when I shout, the frequencies that the classifier are detecting are actually different from the non-shout.

So I'm wondering: does the volume of my shout change the frequencies in my speech, or am I somehow enunciating differently when I shout?

  • $\begingroup$ Could also be a signal to noise ratio problem. Getting a clean microphone pickup is difficult and speaking louder does help with that too $\endgroup$ – Hilmar Oct 15 '20 at 12:20

In a nutshell: yes, it does, at least under certain circumstances.

In a noisy environment, people tend to not only increase their volume when speaking, but also speak in a higher pitch. It's called Lombard Effect, it's well known and you should find plenty of material about it.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

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