资源列表
Natural gradient ML or nonlinear decorrelation alg
- 极小边际熵等价于叉四阶累积量的平方和最小。通过迭代使四阶累积矩阵对角化，实现交叉四阶累积量的平方和的极小化。他是语音识别的重要预处理算法-minimum entropy equivalent to the marginal four bands fork cumulative amount of square and smallest. Through iterative four bands so that the cumulative matrix diagonalization, four
fxlms
- ％％ Active Noise Control Using a Filtered-X LMS FIR Adaptive Filter ％ This demonstration illustrates the application of adaptive filters to the ％ attenuation of acoustic noise via active noise control. - Active Noise Control Using a Filtered-X L
SimpleLM.nightly.tar
- 非常简单的语言模型，能够使得快速的生成语音识别所需的模型
speechfeaextra1
- Short introduction to speech feature extraction code: Step 1: Create speech features: If you have a one stereo file with each speaker in one channel use: features = speech_features_stereo( demo.wav ) If you are using several mo
lpcmel.rar
- 此C++程序同时包含了语音信号的lpc参数，LPC倒谱，以及mel倒谱的提取程序,This C++ program also includes a voice signal lpc parameters, LPC cepstrum, and mel cepstrum extraction procedures
lpcdaopu
- 可以求出语音信号的LPC倒谱特征向量，该特征向量在语音信号分析中得到了广泛的应用。-voice signal can be obtained by LPCCEP eigenvector, the eigenvector of the voice signal analysis has been widely used.
MFCC
- this simple programe for mfcc feature extraction developed in matlab.-this is simple programe for mfcc feature extraction developed in matlab.
yuyingbobao521
- 这是一段很好用的程序，主要用于语音播报521中的例程，只要照着上面的程序写就能驱动语音播报器发出声音-This is section of very easy to use procedures, mainly uses in the pronunciation disseminating news 521 the routines, so long as illuminates the above procedure to write can actuate the pronunciatio
AdaptPrediction
- LMS算法的matlab实现，是基本功能仿真、误差函数曲线等
adpcm
- 用ADPCM算法将语音文件（.wav格式）的16位数据压缩成4位数据的程序，还有将4位压缩后的数据解压成语音文件-ADPCM encoder and decoder
matlabyuyinshibiesuanfa
- matlab语音识别算法，包括预处理，特征提取，训练，识别算法，基于hmm模型-Matlab speech recognition algorithms, including preprocessing, feature extraction, training, recognition algorithm based on model hmm
matlab.rar
- 本程序是语音识别源程序，该方法能节省大量的计算时间，大大减少计算量,This procedure is a source of speech recognition, the method can save a lot of computing time, greatly reducing the computation