资源列表
endpoint-detection
- 基于短时能量和短时平均过零率的语音信号的端点检测程序-Endpoint detection procedures based on short-term energy and zero-crossing rate of the average voice signal
mpelpc
- 此方案基于全极点语音产生模型，编码过程简述如下：首先通过线性预测分析方法提取声道滤波器参数；其次通过合成分析法确定最佳激励矢量；最后将滤波器参数和最佳激励矢量进行编码传输。-This program is based on all-pole speech production model, the encoding process summarized as follows: First, by linear prediction analysis to extract channel filt
hclftest
- 本程序是一个语音回放的实验。 运行程序，对着话筒讲话，等待几秒钟，耳机里会反复重复所讲的话。 -This program is an audio replay of the experiment. Run the program, Duizhaohuatong speech, waiting a few seconds, the headphones will be repeating the words spoken.
yiuyinchuli
- 包含语音端点检测、基本语音处理算法MFCC、LPCC等，具有较高参考价值-Including voice activity detection, basic voice processing algorithms MFCC, LPCC, etc., with high reference value
speech-recognition
- 语音识别系统，包括预处理，汉明窗，梅尔频率倒谱率，离散余弦变换，前置滤波器组，对数能量，滤波器组，基本的滤波器组，dtw-speech recognition system，including Pretreatment, Hamming window, Mel frequency cepstrum rate, discrete cosine transform, pre-filter, log energy, filter, basic filter，dtw
VCANN
- 人工神经网络中部分组成文件VC程序，包括头文件、前向传播、反向传播等等。-Some of the components of an ANN written by VC.
SVM_for_classfication
- 一个基于HMM的说话人识别的源程序程序和列子-Copy all files in Matlab current directory and type "speakerrecognition" on Matlab command window. After unzipping the file correctly, you will find two folders, TRAIN and TEST, each contains some files, named: S
yinyue
- 本代码写是关于音乐的代码，现在上传的只是其中的一部分-This code is written about music code, only part of which is now uploaded
dtw
- dtw完美算法。。是目前为止的完美算法。是当今互联网时代的一个进步-dtw perfect algorithm. . Is now the perfect algorithm
fingerprint
- Type Classification Code: main.m (program control) discretize.m (converts image to discrete values) plotimg.m (plots images) dirImg.m (computes the directional image) extract.m (extracts square portion of image - called by di
wbldq
- 文本朗读源码文件，占用空间超小。未添加录音功能，如需录音功能联系QQ4382584-Text to speech source documents, ultra-small footprint. No recording function, recording function for contact QQ4382584