The Use of Arabic Vowels to Model the Pathological Effect of Influenza Disease by Wavelets

Table 5

The results of the comparison between different state-of-the-art methods based on accuracy for the verification task of speech utterances as vowel “A” as well as the separated words with cross validation 5.

Utter.	Method	System	KNN, CV-5, Acc (%)	EF	SVM, CV-5, Acc (%)	EF
A	LPCC-20	Influenza/normal	82.5	81.2	75.0	74.7
Words	LPCC-20	Influenza/normal	70.0	70.0	67.0	66.9
A	Formants	Influenza/normal	77.0	75.0	82.3	81.3
Words	Formants	Influenza/normal	81.3	81.2	84.4	84.3
A	MFCC	Influenza/normal	89.6	89.4	88.5	88.5
Words	MFCC	Influenza/normal	85.3	84.4	85.3	84.4
A	LPCW	Influenza/normal	91.7	91.6	87.6	86.9
Words	LPCW	Influenza/normal	94.5	93.2	85.3	82.4