Skip to main content
F0 is extracted by _extract_f0_features(sound, audio) using Praat’s autocorrelation method via speech analysis library. | Feature | Unit | | :--- | :--- | | f0_mean | Hz | | f0_std | Hz | | f0_min, f0_max, f0_range | Hz | | f0_confidence | 0–1 | Gender-aware range:
  • Male: 85–180 Hz
  • Female: 165–255 Hz
  • Auto: 75–300 Hz Reduced f0_range correlates with prosodic flatness — a documented marker in major depressive disorder.