资源列表
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.
VQ
- 实现了基于VQ的语音识别系统,里面有自己录的语料,可以实时的录入并识别十个数字的单音字,作为语音识别的初学很有帮助-Realized VQ-based speech recognition system, which has its own record of corpus, real-time entry and word recognition tone ten digits, as speech recognition beginners helpful
noisegen
- 声音的加噪处理,有益于研究声音在噪声环境下的处理情况,提高抗噪性-Adding noise processes sound, useful for researchers sound processing in noisy environments, raising the noise immunity
SpeechRec
- 关于语音识别的倒谱系数算法,可以应用到动态时间规整算法中-About Cepstral speech recognition algorithm can be applied to dynamic time warping algorithm
StartingWithSpeechRecognition
- speaker recognition in real time done with matlab
phone
- 这是一个利用MATLAB实现的电话拨号音的合成与识别的源代码-this is a program by using MALAB
phone2
- 这是一个利用MATLB实现的电话拨号音的合成与识别的源代码-this is a program by using MATLAB
pulseaudio-vad-master
- VAD检测,在linux中语音活性检测,非常实用-VAD detection