A new objective speech quality evaluation method based on weighted Bark spectral distortion (WBSD) is presented.
提出了一种基于加权巴克谱失真(W BSD)的语音质量客观评价算法。
A novel approach to the real-time speech quality evaluation in a packet network using feed-forward multiple class random neural network (FFMCRNN) was presented.
提出了一种利用前馈随机神经网络在分组网络中进行实时语音质量评价的新方法。
In the application of speech quality objective assessment, the result of subjective evaluation under plenty of distortion conditions is directly used as the desired value of training.
结合语音质量客观评价应用，我们以在大量的失真条件下得到的主观评价结果作为期望值对该网络进行训练。
应用推荐