Graphics Reference
In-Depth Information
Fig. 7 Accuracy (%) of
conventional methods using
global features and our
proposal
100
SVM
PNN
80
60
40
20
0
Conventional
Proposal
The network has many advantages compared with other kinds of arti
!
cial neural
networks and nonlinear learning algorithms, including a very fast learning speed
and a small number of parameters.
4 Results
A tenfold cross validation was used to evaluate and test our proposed approaches as
well as make comparisons with previous pieces of research because it is used in
We reviewed all of the most recent research on the aspect of classi
!
ers and found
that the support vector machine (SVM) is one of the most robust and popular
classi
!
ers in the
!
field of affective research, and it beats out many other kinds of
on PNN are compared with those based on SVM (Fig.
7
). Twenty segments with a
length is 50 ms were used for voting in our proposal.
5 Discussion on Segment-Level Features
Previous research has reported on strategies for improving the accuracy of speech
emotion recognition by utilizing segment-level features together with global fea-
tures extracted from utterances. The effectiveness of these strategies was proved in
abandons the global features from utterances. The analytical results indicate the
robustness of this advancement, which leads to a higher level of recognition
accuracy by only using segment-level features in the proposed decision model. We
proposed a segmentation method adopting a correlation coef
!
cient in order to select
the appropriate number of segments within an utterance. Therefore, the generated
segments have less redundant information for the decision model, which contributes
to a better understanding of the utterance label.
