52_HQ

近场的MUSIC算法，可用于近场噪声源识别(Near-field MUSIC algorithm can be used for near-field noise source identification)

MFCC算法的matlab实现,该算法清晰明了，简单易懂，非常的适合初学者。(The realization of MFCC algorithm based on MATLAB)

频域的模态参数识别方法之一，可以对振动信号进行分析处理，得出结构的固有频率，阻尼比，振型系数，方法很好，程序完整(Frequency-domain modal parameter identification methods that can analyze the vibration signal processing, draw the structure of natural frequencies, damping ratio, mode shape coefficient, very good method, program integrity)

本文主要研究普通计算环境下语音自动识别(ASR)技术的软件实时实现，基于语音识别的基本原理和过程。在VC环境下建立了一套语音识别系统及其演示软件。实验表明，该系统对特定人情况有较高的识别率和一定的实时性(In this paper, under the computing environment on general automatic speech recognition (ASR) technology to achieve real-time software, speech recognition based on the basic principles and processes. VC environment in the establishment of a voice recognition system and its presentation software. The experiments show that the systems are in particular have a high recognition rate and a certain degree of real-time)

gmm模型下的语音情感识别系统，GMM只是一个数学模型，只是对数据形态的拟和，但是和你所看到的数据分布存在出入也是正常的，因为用EM估计GMM的那些参数时，一般假设我们所得到的数据是不完备的（也就是说假设我们看到的数据分布不是真正的分布，它在运算时把那部分丢失或者叫隐藏的数据“补”上了）(gmm model speech emotion recognition system, GMM is a mathematical model, but fitting the data form, but you can see there is access to the data distribution is normal, because those with the EM estimated GMM parameters, the general assumption we get the data is incomplete (that is, assuming we see the distribution of the data distribution is not real, it is part of the operation at the time that is lost or hidden data is called " fill" on the))

一种用于语音或者心音去噪和提取包络的预处理方法，对于后面信号处理更加方便(A method for denoising and extract voice or heart sounds envelope pretreatment method, the signal processing is more convenient for the latter)

基于倒谱短时部分反映了语音的声道特性，先用汉明窗取一帧语音，然后经变换得到语音倒谱，将倒谱短时部分取出，进行正交反变换后将得到声道的对数谱，即得到语音频谱的包络。将频谱包络和频谱画在一张图上，有很好的对比效果。获取的包络效果十分好。(Based Cepstral partly reflects the short channel characteristics of the speech, first take a Hamming window with a frame of speech, and speech cepstrum obtained by converting the cepstrum short segment out inverse orthogonal transform to obtain channel will of the spectrum, i.e. to obtain the envelope of the speech spectrum. The spectral envelope and spectral painted on a chart, there is a good contrast. Get the envelope effect is very good.)

语音信号的特征提取，语音信号的Mel倒谱特征（MFCC）的求解方法，语音信号的线性预测原理以及LPC特征的求解方法 (Speech signal feature extraction, speech signal characteristics of Mel cepstrum (MFCC) the solution, voice signals, as well as the principle of linear prediction characteristics of the LPC method)

谱减法自适应滤波以及听觉掩蔽效应00865833(Spectral subtraction )

attention model for saliency detection.