Digital Signal Processing Reference
In-Depth Information
speech utterances of two male and two female speakers from the TIMIT
database are used in our study. Four different background noises are taken
from the Noise-92 database. Segmental SNR (SegSNR) improvement is used
for assessing the enhancement performance. The results are shown in Table
11-1. It can be seen that the proposed algorithm leads to higher SegSNR
improvements than TSVD for all noise types and levels.
Figure 11-2.
Reconstruction of Unvoiced Speech Signal.
