The description precision of the excitation signal greatly influences the quality of reconstructed speech in low bitrate vocoders.
在低速率声码器中,对激励信号的描述直接影响重建语音的质量。
In the environment of speech coding application, especially in military applications, the vocoders quality in noisy environment needs to be improved.
在语音编码的应用环境中,特别是在军事应用中,强噪声环境下声码器性能的改进是一个亟待解决的问题。
MELP vocoders utilize mixed pulse and noise as the excitation to elimate the buzzes in traditional LPC vocoders, and add a jitter voicing state to overcome the tonal noise.
MELP声码器采用混合脉冲和噪声激励解决了经典LPC的嗡嗡声的问题; 引入了抖动浊音状态以克服音调噪声;
Using different feature vectors, the effect of the vocoders differs on speaker dependent continuous speech recognition and speaker independent connected digits recognition.
对于特定人连续语音识别系统和非特定人连接词识别系统,在使用不同的特征矢量时,不同编码器产生的识别效果有比较大的差异。
At last, this paper introduces a speech and data multiplexed based on Multi-CPU and VLSI vocoders. The operating principle and characteristics of the multiplexed are analyzed.
介绍了采用多cpu系统和VL SI声码器为核心的语音数据复接器,分析了系统的工作原理和特点。
At last, this paper introduces a speech and data multiplexed based on Multi-CPU and VLSI vocoders. The operating principle and characteristics of the multiplexed are analyzed.
介绍了采用多cpu系统和VL SI声码器为核心的语音数据复接器,分析了系统的工作原理和特点。
应用推荐