specsubm

实验示例是基于语音中的mfcc，语音倒谱特征来进行聚类，先利用训练样本来计算训练样本聚类中心（用到了lbg算法），之后再进行分类。 注意：使用代码时需要自己更改文件路径。(This example is based on the MFCC in speech and the feature of speech Cepstrum to cluster. First, the training sample is used to calculate the training sample clustering center (using the LBG algorithm), then the classification is then carried out.)

这是一个基于DTW的语音识别的代码，里面包含端点检测和MFCC的提取。(This is a DTW-based speech recognition code, which contains end point detection and the extraction of MFCC.)

实现在单信道语音信号处理中的降噪，用Spectral Subtraction算法实现的，内涵音频文件，代码中包括给纯净音频文件加噪声的部分。(Noise reduction in single-channel speech signal processing, using the Spectral Subtraction algorithm, the connotation of an audio file, the code in the package Including pure audio files and part of the noise.)

一个对有噪声的音频信号进行自相关滤波的c程序，用的turbo c 3.0工具(One pair of noisy audio signal autocorrelation filtering c program using turbo c 3.0 Tools)

信息融合方面得例题，对已知要求的目标，利用动态矩阵控制（DMC）使其达到期望值。所有程序均已通过调试。希望对大家有所帮助(Example of information integration have on the known requirements of the target, the use of Dynamic Matrix Control (DMC) to reach the expectations. All have been through the debugging process. I hope all of you to help)

C语言fft和ifdct的函数，可以直接使用(C language functions fft and ifdct can be directly used)

实现mffc求解 并且可利用hmm进行孤立词识别(Solving mffc realize and can be used for isolated word recognition hmm)

一个对有噪声的音频信号进行自相关滤波的c程序，用的turbo c 3.0工具(One pair of noisy audio signal autocorrelation filtering c program using turbo c 3.0 Tools)

应用LBG算法对语音信号进行矢量量化。本压缩包共有两个主文件，training.m对训练数据进行处理并得到四个初始码本，quantizing.m对待量化数据进行矢量量化。其余为自编功能函数。(application of voice signal VQ. The compressed into two main documents, training.m right training data to be processed and four of the initial code, quantizing.m treat quantitative data for vector quantization. The remainder self-function.)

语音识别，实现语音的识别功能，，特定人的语音识别。识别0~9的发音(Speech recognition, voice recognition function, a particular person' s speech recognition. Identify the pronunciation of 0 to 9)