Skip to main content
EURASIP Journal on Advances in Signal Processing

Table 5 PESQ scores with background noise reduction.

From: Transient noise reduction in speech signal with a modified long-term predictor

Algorithm

Input

STP

STP and LTP

LTP with

Eq. (5)

LTP with

Eq. (13)

LTP with

Eq. (14)

Female 1

2.57

2.76

2.75

3.11

3.17

3.17

Female 2

1.57

1.76

1.77

2.65

2.70

2.69

Female 3

1.44

1.83

1.82

2.74

2.70

2.86

Female 4

1.99

1.98

2.04

2.69

2.67

2.77

Male 1

1.86

2.15

2.14

2.89

3.09

3.10

Male 2

1.21

1.53

1.51

2.63

2.74

2.81

Male 3

2.44

2.57

2.55

3.13

3.16

3.15

Male 4

1.81

2.04

2.00

2.74

2.83

2.82

Average

1.86

2.08

2.07

2.82

2.88

2.92

  1. The PESQ scores of input and enhanced signals utilizing various speech modeling filters before the transient noise reduction. The input signals are firstly processed by the OM-LSA estimator to remove the background noise. The first row represents the methods applied before median filtering. The first column denotes the kind of desired speeches.
Back to article page