comfort noise generation system
回声消除中舒适噪声的作用
Fig. 3 shows the speech signal at the input of the echo canceller.
It consists of the speech of the near-end speaker and the far-end echo.
Fig. 4 shows the output signal from the echo canceller with unsuppressed residual echo.
Fig. 5 contains the signal coming out from the echo suppressor.
It could be seen that residual echo was suppressed together with the background noise.
The result is a channel that suddenly sounds dead.
The far-end listener may think that the call was disconnected.
The proposed CNG-VAD algorithm was designed to prevent this.
Fig. 6 shows the signal Sout at the output of the CNGVAD system.
The suppressed background noise is successfully replaced by the artificially generated comfort noise.
Fig. 3: 包含回声的speech信号.
Fig. 4: 回声消除的输出信号，还没有对残余回声进行抑制。
Fig. 5: 经过回声抑制之后的输出。可以看出，除了残余回声，背景噪声也一同被抑制了。导致的结果就是，这段时间听起来像是断线的。CNG-VAD算法就是为了防止这个。
Fig. 6:加入舒适噪声之后的输出。可以看出，被抑制的背景噪声被人工生成的舒适噪声取代。
References:
