多脉冲激励线性预测编码(MPLPC)方法中,合成滤波器的阶数是固定的。
The order of synthesis filter is fixed in multi-pulse excited linear prediction coding(MPLPC) method.
通过在浊音段提取多脉冲激励信号加入语音的状态方程,有效地重建语音的高频谐波。
By extracting the multipulse excitations during voiced speech, and adding the excitations into the process equation the harmonic of high-frequency area can be reconstructed.
本文针对语音多脉冲激励模型,提出了量化网络的结构和学习规则,并将此方法和传统方法进行了比较。
We provide the architecture and learning rule of the quantizing network, and compare it with the traditional method in the implementation.
本文针对语音多脉冲激励模型,提出了量化网络的结构和学习规则,并将此方法和传统方法进行了比较。
We provide the architecture and learning rule of the quantizing network, and compare it with the traditional method in the implementation.
应用推荐