This node adds white noise to input signals.
No files are required.
This node is used to add white noise to input signals, thus reducing the influence of nonlinear distortions after separation. For example, since PostFilter performs nonlinear processing, it is difficult to avoid musical noise, which may greatly influence the speech recognition performance. The influence of such noise can be reduced by adding an appropriate amount of known white noise.
When to use
An example is shown in the figure.
Parameter name 
Type 
Default value 
Unit 
Description 
LENGTH 
512 
[pt] 
FFT length 

WN_LEVEL 
0 
Additional noise level 
Input
: Map<int, ObjectRef> type. Since ObjectRef is of Vector<complex<float> > type, signals of the frequency domain are input.
Output
: Map<int, ObjectRef> type. Since ObjectRef is of Vector<complex<float> > type, signals to which white noise has been added are output.
Parameter
: FFT length; must be equal to the other nodes.
: Additional noise level. Designate the maximum amplitude in the time domain.
The following is added to each frequency bin of input signals.
\begin{equation} \frac{\sqrt {\rm LENGTH}}{2} \cdot {\rm WN\_ LEVEL} \cdot e^{2 \pi j R} \end{equation}  (149) 
$R$ indicates a random number of $0 \le R \le 1$ (different for each frequency bin). $\sqrt {\rm LENGTH}/2$ is used to revise distortions of scaling between the time and frequency domains that occur during frequency analysis by FFT.