资源列表
lpc
- 读入一段语音信号，通过自相关法求s的均方预测误差为最小的预测系数-Read into a voice signal s, by the autocorrelation method and the mean square prediction error for the smallest prediction coefficients
jc
- matlab实现加汉明窗，矩形窗，并对它们进行傅里叶变换，并实现频谱的分析。-matlab realize Jia Hanming window, rectangular window, and they are subjected to Fourier transform, and to achieve the analysis of the frequency spectrum.
mfcc
- 这是基于matlab的关于Mel频率倒谱系数（MelFrequencyCepstrumCoefficient，MFCC）的代码，对大家理解有一定帮助。-This is based on the matlab Mel Frequency Cepstral Coefficients (MelFrequencyCepstrumCoefficient, MFCC) code for us to understand some help.
lpc
- LPC提取共振峰，由matlab平台实现,是一种提取共振峰信息的有效方法.-from Matlab platform is a resonance peak extraction of information in an effective manner.-LPC formant extraction, implemented by the matlab platform is an effective method to extract formant information.-From Ma
AMDF
- 采用AMDF法提取基音周期，并根据男女生基音频率的不同，识别说话人性别。-Gender recognization based on AMDF
MusicRecogniseding
- 国科大数字信号处理2课程，基于Python的哼唱识别，有乐库的-ucas digital signal processing 2 courses, humming recognition based on Python, there is music library
speech_vad
- 利用MATLAB来实现语音的分帧及语音端点检测(Using MATLAB to achieve voice segmentation and voice endpoint detection)
kano
- 用matlab演奏卡农，一个matlab的发声小程序(play Cannon using matlab)
train
- 基于BP网络和多特征的语音端点检测，提取自相关函数最大值和频带方差作为BP网络输入，输出判断是否为语音信号。(A Speech Endpoint Detection Algorithm Based on BP Neural Network and Multiple Features)
specsub_modified11
- 语音唤醒就是在设备待机状态下，用户说出特定的语音指令（唤醒词）使设备进入工作状态或完成某一操作。设备为了实现语音唤醒功能，就需要设备实时监听，也就是实时的录音并分析有没有唤醒词来唤醒设备。评价一个语音唤醒系统的标准有三个：唤醒正确率、误报率、功耗。一般情况下，唤醒正确率越高 ，误报率也越高。好的系统就需要唤醒率高，误报率低，功耗低。(Speech wakeup is when the device is in standby mode, the user speaks a particular
ICA
- 本程序音频共有四个，借助鸡尾酒会问题思想，用ica算法实现四个音频的分离(The audio program for a total of four, with the help of the cocktail party problem, realizing the separation of four audio using ICA algorithm)
yuputu2
- 语谱图的横坐标是时间，纵坐标是频率，坐标点值为语音数据能量。由于是采用二维平面表达三维信息，所以能量值的大小是通过颜色来表示的，颜色深，表示该点的语音能量越强。(The spectral abscissa graph is time, the vertical axis is the frequency of speech data for energy point coordinates. Since the two-dimensional information is expressed i