Skip to main content

Table 8 Comparison of results of artificial data with different parameter of β and combination methods for speaker identification

From: Distant-talking speaker identification by generalized spectral subtraction-based dereverberation and its efficient computation

 

Number of impulse response

 

Parameter (β)

condition for test (%)

Average (%)

4

5

6

7

8

(0.05)

92.4

85.2

84.6

85.8

90.5

87.7

(0.10)

95.0

90.1

89.9

89.0

89.6

90.7

(0.15)

96.2

91.1

91.4

90.1

92.3

92.2

(0.20)

95.2

89.5

90.2

89.9

90.5

91.1

(0.25)

93.5

90.2

87.7

88.0

91.2

90.1