Skip to main content

Table 2 Objective quality evaluation results of enhanced signals.

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

Algorithm

Without OM-LSA

With OM-LSA

 

SNR

SSNR

LSD

SNR

SSNR

LSD

Input

- 4.97

- 11.15

23.10

- 2.67

- 8.67

21.03

STP

- 2.74

- 10.49

22.12

7.70

- 0.78

13.31

STP and LTP

- 2.65

- 10.51

22.44

- 1.25

- 8.35

20.53

LTP with Eq. (5)

5.96

- 3.31

15.16

7.70

- 0.78

13.31

LTP with Eq. (13)

5.88

- 3.14

14.82

7.58

0.64

12.29

LTP with Eq. (14)

6.68

- 2.52

14.26

9.06

0.50

12.74

  1. The SNRs, SSNRs, and LSDs between enhanced signals and desired speech which are measured in both speech presence and absence regions.