搜索资源列表
Matlab_MPEG_1_2_8
- 比较经典的根据MPEG1心理声学模型计算人耳掩蔽曲线的源代码-more classic under MPEG1 psychoacoustic model ear masking curve of the source code
zcpa
- 过零峰值幅度(ZCPA：Zero-cro ingwithPeakAmplitude)特征的语音识别系统，它是基于人耳的听觉模型建立起来的，这是ZCPA的源程序。-Zero-crossing peak amplitudes (ZCPA: Zero-cro ingwithPeakAmplitude) features voice recognition system, which is based on the model of the human ear
audio
- 人耳听觉特性的描述，作音频开发的工程师一定要看一看。-A descr iption of human auditory characteristics for audio development engineer was required to take a look at.
Audio-Processing
- 音频系统，coding, modulation, AWGN, 通过最小距离探测码元，解码，播放。根据不同的SNR，测试在多小的SNR情况下，人耳能识别音频。-Audio systems, coding, modulation, AWGN, by minimizing the distance detection symbol, decoding, playing. Depending on the SNR, the test in the case of multiple small SNR,
mfcc
- 语音识别MFCC特征提取matlab代码。 「梅尔倒频谱系数」（Mel-scale Frequency Cepstral Coefficients，简称MFCC），是最常用到的语音特征，此参数考虑到人耳对不同频率的感受程度，因此特别适合用在语音辨识。-Speech recognition MFCC feature extraction matlab code. \ Mel cepstrum coefficient (Mel- scale Frequency Cepstral Coefficien