Different people reading the same sentences, we can know from the voice who is speaking.

What makes the voice distinguishable?


Some possible perceivable differences might include:

  • differences in pitch frequency (bass vs. soprano voice, etc.)
  • differences in overtone series (formants, head resonances, accent)
  • variations in modulation of pitch over time (vibrato, tremolo, accent)
  • differences in voiced to unvoiced ratios (raspiness?)
  • variations in typical durations of each vowel or consonant
  • variations in cadence modulation (accent?)
  • differences in choice of phonemes for each word or phrase (accent?)

A simple way to solve your problem would be to record a short sentence and then calculate the FFT. This will give you an average spectral fingerprint for that person. Then you can compare spectra in order to identify a given person.

Check some more details here:



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.