An Analysis of Acoustic Features in Reading Speech from Chinese Patients with Depression

This paper investigates acoustic features of depression patients in voice quality and formants, from the perspective of experimental phonetics. The analysis on voice quality based on large samples shows that jitter, shimmer and HNR can distinguish the patients with different degrees of depression, while F0, standard deviation of F0 and HNR can distinguish depression patients from non-patients. These features indicate that the voice of patients tends to be hoarse and rough, with a lower pitch falling into a narrower range. The analysis on formants shows that depression patients tend to centralize monophthongs and simplify diphthongs, reflected by a lower opening degree and slower movement of tongue. Moreover, the patients tend to show a lower spectrum energy than healthy people. Finally, our analysis results suggest that these acoustic features can be used as objective markers for recognition of depression.