From Joyous to Clinically Depressed: Mood Detection Using Spontaneous Speech

Depression and other mood disorders are common and disabling disorders. We present work towards an objec-tive diagnostic aid supporting clinicians using affective sensing technology with a focus on acoustic and statis-tical features from spontaneous speech. This work in-vestigates differences in expressing positive and nega-tive emotions in depressed and healthy control subjects as well as whether initial gender classification increases the recognition rate. To this end, spontaneous speech from interviews of 30 subjects of each depressed and controls was analysed, with a focus on questions elicit-ing positive and negative emotions. Using HMMs with GMMs for classification with 30-fold cross-validation, we found that MFCC, energy and intensity features gave highest recognition rates when female and male sub-jects were analysed together. When the dataset was first split by gender, root mean square energy and shimmer features, respectively, were found to give the highest recognition rates in females, while it was voice qual-ity for males. Overall, correct recognition rates from acoustic features for depressed female subjects were higher than for male subjects. Using temporal features, we found that the response time and average syllable duration were longer in depressed subjects, while the in-teraction involvement and articulation rate wesre higher in control subjects.