资源列表
GMM
- k-means下的GMM训练模型,文档中包含源文件和头文件,详细介绍了如何用GMM去你和数据-GMM Model used by k-means and EM,
weina
- 语音维纳滤波,对语音段添加白噪声,然后通过维纳滤波器对其进行滤波-Wiener filtering for speech
A-Vector-Quantization-Approach-to-Speaker-Recogni
- Speaker recognition based VQ
DELPHICTI
- 使用dephi开发东进语音卡,实现电话银行功能(主叫功能)-voice borad design
HTK-Speech--recognition
- 运用HTK工具箱搭建了一个语音识别系统,可直接运行,参考价值大-HTK toolkit application to build a speech recognition system can be run directly reference the large value
ampp
- 用于提取语音信号的能量谱的函数,ampp(s,a,b,c),x为输入信号,a,b,c用于指定subplot函数的作图位置-A function for extracting the energy spectrum of the speech signal, ampp (s, a, b, c), x is the input signal, a, b, c is used to specify the location of subplot mapping function
zcrr
- 用于计算语音信号过零率的函数zcrr,zcrr(x,a,b,i),x为输入,a,b,c为指定subplot函数的参数-Function zcrr for calculating zero-crossing rate of the speech signal, zcrr (x, a, b, i), x is the input, a, b, c as a function of the parameter specifies subplot
zernik
- Zirnek Moment for image
DTW
- 在孤立词语音识别中,最为简单有效的方法是采用DTW(Dynamic Time Warping,动态时间归整)算法,该算法基于动态规划(DP)的思想,解决了发音长短不一的模板匹配问题,是语音识别中出现较早、较为经典的一种算法,用于孤立词识别。HMM算法在训练阶段需要提供大量的语音数据,通过反复计算才能得到模型参数,而DTW算法的训练中几乎不需要额外的计算。所以在孤立词语音识别中,DTW算法仍然得到广泛的应用。-In isolated word speech recognition, the mos
yuyinchuli
- 语音信号的时域修正——变调或变速语音的播放实现,matlab代码,一完整的项目,外带GUI界面 -Time-domain speech signal correction- tone or voice playback speed achieve, matlab code, a complete project, packed GUI interface
mfcc
- 本段程序实在MATLAB环境下对输入的语音序列x进行MFCC参数的提取,返回MFCC参数和一阶差分MFCC参数。-Voice input sequence x extracted MFCC parameters, return parameters and the first-order difference MFCC MFCC parameters
vad
- 该段程序是求取一段语音的起始和终止点坐标,以达到端点检测的目的。-This section of the program is to strike a starting and ending point coordinates a voice in order to achieve the purpose of endpoint detection.