Evaluation of influence of spectral and prosodic features on GMM classification of Czech and Slovak emotional speech

EURASIP Journal on Audio, Speech, and Music Processing

Table 3 Structure of the feature set P3

Number	Name	Type	Frame	Value
1	HNR	Complementary spectral	Voiced	Mean
2	HNR	Complementary spectral	Voiced	Std
3	HNR	Complementary spectral	Voiced	Rel. max
4	SC	Complementary spectral	Voiced	Mean
5	SC	Complementary spectral	Voiced	Std
6	SFM	Complementary spectral	Voiced	Mean
7	SFM	Complementary spectral	Voiced	Std
8	SE	Complementary spectral	All	Mean
9	SE	Complementary spectral	All	Std
10	F0	Supra-segmental	Voiced	Median
11	F0	Supra-segmental	Voiced	Std
12	F0_DIFF	Supra-segmental	Voiced	Rel. max
13	Jitter	Supra-segmental	Voiced	Median
14	Shimmer	Supra-segmental	All	Max
15	Shimmer	Supra-segmental	All	Median
16	Shimmer	Supra-segmental	All	Rel. max