搜索资源列表
flexica
- 这是实际环境中语音信号盲分离的最新程序代码,用于语音信号独立分量分析ICA。解压后运行,输入录制的混合语音信号即可看到结果。-this is the actual environment of the speech signal separation blind to the latest code, Voice Signal for independent component analysis ICA. Unpacked operation, the importation of record
2006114
- 录音部分是参照vckbase的录音api代码,结合了一小段socket(TCP)就可以用来单方说话录音了,程序分两部分一部分是(录音机+网络发送代码),一部分是(接收数据+播放波形音乐代码),由于程序只是为了自己用,很多地方没有注意错误的识别,结构也比较乱,本程序当初最头疼的就是控制损耗内存,结果用了双缓存来存储波形数据来交替的存储/清除. -part of the recording light vckbase recording api code combination of a small
ALLPASS
- 利用全通滤波器的原理对于因信号进行改变相位,嵌入数字水印-use of the all-pass filter principle as a result of changes in signal phase, embedded digital watermarking
MATLAB-YUYINSHIBIE
- 完整的基音识别程序,经过修改,测试正确。包含基音检测,DTW,LPCC,MFCC提取等-integrity of the pitch identification procedures, the result of the revision, the test correctly. Pitch Detection included, DTW, LPCC Features, MFCC extraction
隐含层为mexihat 输出为sigmal的wav-sigal
- 用三层小波神经网络实现的与文本无关说话人识别。(识别部分)。输入的是语音特征,输出的是识别结果。训练用的语音特征要事先提取出。-with three wavelet neural network has nothing to do with the text of Speaker Recognition. (Recognition). The admission of voice features, the output is the result of recognition. Trainin
GMM.rar
- 完整的语音识别程序,训练模型固定。可以运行出识别结果的~,entire speech recognition programme,with the trainning model given.On matlab,we can get the result of recognition.
vq
- 语音识别VQ全过程的matlab程序,运行测试能出结果,希望对你们有用,实在没点数才把自己压箱底的东西拿出来,-VQ whole process of speech recognition matlab program, run the test to the result, I hope helpful for you, only then it did not point out what their own bottom pressure, the hum
amdf
- 语音识别全过程的matlab程序,运行测试能出结果,希望对你们有用,实在没点数才把自己压箱底的东西拿出来,-The whole process of speech recognition matlab program, run the test to the result, I hope helpful for you, only then it did not point out what their own bottom pressure, the hum
lpcc1
- 语音识别线性预测系数lpcc提取全过程的matlab程序,运行测试能出结果,希望对你们有用,实在没点数才把自己压箱底的东西拿出来,-Voice recognition linear prediction coefficient lpcc the whole process of extraction matlab program, run the test to the result, I hope helpful for you, it is only then did their own p
soundruler_script_0932
- SoundRuler是一个用来分析和图形化重复声音的工具(生物声学)。它识别和测量文件中每种声音的时间和光谱属性。执行的结果可以保存到电子数据表,也可以导出波形图。-SoundRuler is uses for to analyze and the graph repetition sound tool (biological acoustics). It distinguishes and surveys in the document each kind of sound time an
silence_remove
- This code is used to remove silence from a voice signal so that the recognition in voice recognition will give good result. The method is Scale on threshold applied to the envelope for detecting scilence periods. The actual threshold is computed by m
hardreg
- hardreg,经过编译仿真,结果正确,具有良好的移植性。-hardreg, compiled simulation, the result is correct, has good portability.
firfilt
- 实现有限冲击响应滤波器,很完善,很好用,功能很强。只要输入语音或音频文件及滤波器系数,就可得到结果。-Implementation of FIR filter. Very good and powerful. Input speech/audio file, and filter coefficients, then you can get the output result.
iirfilt
- 实现无限冲击响应滤波器,很完善,很好用,功能很强。只要输入语音或音频文件及滤波器系数,就可得到结果。-Implementation of IIR filter. Very good and powerful. Input speech/audio file, and filter coefficients, then you can get the output result.
mfcc
- 用MATLAB分别编写了通过MFCC,EDP,LPC处理后的语音信号-Sound signal is treated by MFCC,EDP,LPC and show the final result.
mfccdtw
- 先用端点检测将语音中有用的语音部分提取出来(即将头部和尾部的静音部分除掉),然后用LPC算法提取语音信号的特征参数,进行动态归整(DTW算法)后与模板库里面的标准语音作比较,最后将识别结果进行D/A转化后播放出来。在本部分的设计中,则主要完成语音识别的模式匹配算法部分的软件实现。 -First with the endpoint detection of speech to voice some of the useful extracted from the (soon to mute som
mic1
- There are four major types of adaptive filtering configurations adaptive system identification, adaptive noise cancellation, adaptive linear prediction, and adaptive inverse system. All of the above systems are similar in the implementation of the al
Speakerrecognitionbased-on-MFCC
- 这是一篇工学硕士论文,主要说关于说话人语音识别,,以支持向量机为分类器,分别以MFCC和IM-FCC为特征单独执行分类,将得到结果按某种方式融合,取两者之长,最后做出判决来提高说话人识别系统的性能。-Speaker recognition is a kind of technology that take the use of the information contained in the speech signal to identify who is the speaker or to
speech-recognition-system
- A robust speech recognit ion system based on discriminative learning of environmental features is proposed for recognit ion of environmental features in high noise background, and a g radient descent algo rithm was adopted for parameter
FFT-CPP
- 可读取一个二进制文件(如去掉头部的wav文件),将得到的数值进行FFT求出离散频谱值并保存到一个文件中。-This will process the data read from a file by FFT computing, and then save the result to a new file.