Skip to main content

Table 4 Results of % recognition for different cases by the HMM models

From: Significance of parametric spectral ratio methods in detection and recognition of whispered speech

Case

Number of files

% Recognition

Case 1

493

80.53

Case 2

200

63.00

Case 3

250

33.20

Case 4

493

58.42

Case 5

200

47.50

Case 6

250

50.40

Case 7

209

45.93