Mental diseases are increasingly common. Among these, bipolar disorders heavily affect patients’ lives given the mood swings ranging from mania to depression. Voice has been shown to be an important cue to be investigated in relation with this kind of disease. In fact, several speech-related features have been used to characterize voice in depressed speakers. The goal is to develop a decision support system facilitating diagnosis and possibly predicting mood changes. Recently, efforts were devoted to studies concerning bipolar patients. A spectral analysis of F0-contours extracted from audio recordings of a text read by bipolar patients and healthy control subject is reported. The algorithm is automatic and the obtained features describe parsimoniously speech rhythm and intonation. Bipolar patients were recorded while experiencing different mood states, whereas the control subjects were recorded at different days. Feature trends are detected in bipolar patients across different mood states, while no significant differences are observed in healthy subjects.
展开▼
