Comparing objective feature statistics of speech for classifying clinical depression

Abstract

Human communication is saturated with emotional context that aids in interpreting a speakers mental state. Speech analysis research involving the classification of emotional states has been studied primarily with prosodic (e.g., pitch, energy, speaking rate) and/or spectral (e.g., formants) features. Glottal waveform features, while receiving less attention (due primarily to the difficulty of feature extraction), have also shown strong clustering potential of various emotional and stress states. This study provides a comparison of the major categories of speech analysis in the application of identifying and clustering feature statistics from a control group and a patient group suffering from a clinical diagnosis of depression.

A comparative study of different classifiers for detecting depression from spontaneous speech

“…Although depressed speech has a monotone characteristic indicated by changes in pitch and formants [4,3,25], their performances here were not as good as expected. That might be an indication that pitch and formants features are more suitable in a speaker-dependent comparison.…”

A review of depression and suicide risk assessment using speech analysis

“…for longer than a two-week period.The DSM has often been criticised for the homogenous264 way it defines the boundaries between mental illnesses,265 leaving diagnosis open to subjective biases where a proper 266 patient assessment does not have to be done to achieve a267 diagnosis (Brown et al, 2001; Kamphuis and Noordhof, 268 2009; Lux and Kendler, 2010; Oquendo et al, 2008; Stein 269 et al, 2010; Watson, 2005). Noting that at least four of 270 the DSM symptoms listed in Table 1 comprise two distinct 271 manifestations, there are at least 1497 unique profiles of 272 depression (Østergaard et al, 2011).…”

Detecting depression: A comparison between spontaneous and read speech

“…Finally, the pitch features, which have been widely investigated, show a lower range of fundamental frequency (F0) in depressed [3,12,13,14], which increases after treatment [4]. The lower range of F0, indicate a monotone speech [15] and its low variance indicate a lacking of significant expression in depression [7].…”