Table 8.
The top 10 negative correlated features with their description, r value(strength of correlation and direction)
| S no | Feature Name | Description | r value |
|---|---|---|---|
| 1 | AU 25 skewness (A_25_S) | Lips part count skewness | -0.44741 |
| 2 | Fraction of locally unvoiced frames (F_L_U) | It is a fraction of pitch frames analyzed as unvoiced pitch (pitch is 75Hz) frames in a voice. | -0.3891 |
| 3 | Degree of voice (D_V_B) | This measure is total duration of breaks between the voiced parts of the speech signal | -0.3784 |
| 4 | AU 10 skewness (A_10_SK) | Upper lip raiser skewness | -0.36990 |
| 5 | AU 09 skewness (A_9_S) | Nose wrinkle skewness | -0.34867 |
| 6 | AU 25 kurtosis (A_25_K) | Lips part kurtosis | -0.34069 |
| 7 | Pitch Skewness (P_SK) | It is pitch’s skewness | -0.3217 |
| 8 | AU 12 skewness (A_12_SK) | Lip corner puller skewness | -0.3195 |
| 9 | Shimmer APQ3 (SAQ) | It is the average absolute difference between the amplitude of a vocal period and the average of the amplitudes of it and its 2 closest neighbours, divided by the average amplitude. | -0.312 |
| 10 | Mean absolute differences shimmer(MDS) | Average absolute difference between consecutive differences between the amplitudes of consecutive periods. | -0.3129 |