Digital Signal Processing Reference
In-Depth Information
A
H
A
H
H
H
H
H
H
0
500
1000
1500
samples
(a) Stationary voiced speech
A
N
A
H
H
HHHH
0
500
1000
1500
samples
(b) Unvoiced speech (second frame)
Figure 9.33
Classification of male speech corrupted by babble noise (10dB SNR):
A (ACELP), H (harmonic), and N (noise excitation)
The secondary classification performs very similarly under the clean speech
conditions, except for the occasional classification of frames as ACELP, which
were originally classified as harmonic under the clean speech conditions
(compare Figures 9.31a and 9.32a). This is due to the inability of the harmonic
model to adequately synthesize the corrupted signal and themodel parameter
Search WWH ::
Custom Search