![]() To combine these two systems, resulting in a 6% relative improvement in accuracy in comparison with the i-vector system based on MFCCs alone. Voice quality features performed as well as MFCCs. ![]() An i-vector-based system using Mel FrequencyĬepstral Coefficients (MFCCs) and another using voice quality features was developed. The features (F0, F1, F2, F3, H1-H2, H2-H4, H4-H2k, A1, A2, A3, and CPP) were inspired by a psychoacoustic model of voice quality. In order to capture various aspects of speech signals, we used voice quality features in addition to conventional cepstral features. Leveraging this unique and extensive database, we built an i-vector framework. We used a database comprised of recordings of interviews from a large number of female speakers: 735 individuals suffering from depressive (dysthymia and major depression) and anxiety disorders (generalized anxiety disorder, panic disorder with or withoutĪgoraphobia) and 953 healthy individuals. In this study, we focused on addressing these variabilities. Automatic assessment of depression from speech signals is affected by variabilities in acoustic content and speakers. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. Archives
June 2023
Categories |