资源列表
hubot-scripts-master
- 这些是用于您的公司的hubot的社区脚本的集合,一个聊天机器人,查看hubot-scr ipt-catalog,查看所有可用脚本的列表和描述。-These are a collection of community scr ipts for hubot, a chat bot for your company.Check out the hubot-scr ipt-catalog for a list and descr iption of all the available scr ipts.
Baidu_Voice_RestApi_SampleCode
- 百度官方语音识别SDK,demo演示。(学习参考) 上传WAV录音,在线识别为文字,大数据云技术。 建义百度: 百度语音SDK,最好增加所有编程语言的例子,这样用其他语言的人下载直接编绎就能用了 可以让网友自行上传,你们审核一下就行了。 最好还可以让我们发一些作品上去,最好可以弄成收费,便宜点也可以呀,有竟争才有进步 。 -Baidu official voice recognition SDK, demo demo. Upload WAV recording
SoundCutTest
- 耳朵的声音完成韵律分割。 在测试中,效果相当不错。-The sound of the ear to complete the rhyme segmentation. In the test, the effect is pretty good.
plv_measure
- this function computes phase synchronization using Phase locking value method over an analysis window of fixed length inputs to this function - phase, sampling frequency output this function - synchronization measure based on PLV processing perform
EWT
- 经验小波变换结合EMD的自适应性和小波分析的理论框架,Gilles提出了一种称为经验小波变换(EWT)的自适应信号处理方法.其核心思想是通过对信号的Fourier谱进行自适应划分,建立合适的小波滤波器组来提取信号不同的AM-FM成分.-Empirical wavelet transform
DSP
- DSP实现基于LPC的语音基频提取算法,包含采样、fir滤波器,LPC算法等的编写 -The realization of the speech pitch extraction algorithm based on LPC
Extract-Sound-Feature
- 利用matlab提取声音的基本特征,包络、MFCC、声谱图、能量。代码不复杂,但是省去大家找这些的时间。-The basic feature extraction using matlab sound envelope, MFCC, sonograms, energy. Code is not complicated, but we look for these omitted time.
VolumeControl
- Vb音量控制源码,麦克风音量调整,值得收藏的源码程序-Vb volume control source, microphone volume adjustment, it is worth collecting the source program
CZTtransformer
- CZT运算是在z域以任意螺线采样,源码采用512点做CZT运算求出频域最大值-CZT operation is in the Z domain to arbitrary spiral sampling, the source code using 512 points to do CZT operations to calculate the maximum frequency
G.729a-gst
- G.729a位取反,信噪比测试代码。MFC编写的,测试可用。-G.729a bit inversion, signal to noise ratio test code
HMM-master
- This code is to integrate HMM and HTK
Voice-endpoint-detection
- 语音识别检测端点也就是采集声音信号的时候,开始说话到说话结束,我们把这一段声音信号采集下来进行处理。不然那么多信号都去处理,没有声音也处理那就浪费了很多的空间以及浪费了CPU去做后续的操作。这是一段语音识别检测端点代码。-Speech recognition detection endpoint is to collect the sound signal, began to speak to the end of the speech, we put this section of the s