搜索资源列表
ICA
- fastica语音分离 3个混合的语音信号，分离开来-fastica speech separation
GMM
- 混合高斯模型的C++程序，封装成为C++的类，直接调用即可。-gaussian mixture model train code
RLS_filter
- RLS算法，编写了MATLAB程序实现自适应干扰对消。给出信号实例，用于验证所编写程序的性能。所给信号为：①噪声与语音的混合信号——signalnosie.wav；②噪声信号——noise.wav。两信号均为立体声，PCM压缩，采样速率为48000Hz，采样精度16bits。-RLS algorithm, the preparation of a MATLAB program to achieve adaptive interference cancellation. Given signal
IPMSG2007
- 飞鸽传书2010最新版.支持内、外网、混合网络互通的多媒体飞鸽系列软件，具备表情、截图、语音、视频、远程控制多媒体通讯功能，绿色软件即装即用，内联飞鸽传书，-Flying Pigeon 2010, the latest version of pass books. Support inside and outside the network, hybrid network of interoperable multimedia Flying Pigeon series of software,
useful
- Visual C++与Matlab混合编程实现语音识别-Visual C++ and Matlab programming hybrid speech recognition
acdc
- 语音信号处理--分离混合语音信号的很好的程序，编程水平极高，值得学习。-Speech signal processing- Separation of mixed speech signals, a very good program, a high level of programming, it is worth learning.
GMM
- 语音识别 高斯算法程序 高斯混合模型 源代码- specch recognition
speech-emotion-recognition
- 过特定人语音情感数据库的建立；语音情感特征提取；语音情感分类器的设计，完成了一个特定人语音情感识别的初步系统。对于单个特定人，可以识别平静、悲伤、愤怒、惊讶、高兴5种情感，除愤怒和高兴之间混淆程度相对较大之外，各类之间区分特性良好，平均分类正确率为93.7 。对于三个特定人组成的特定人群，可以识别平静、愤怒、悲伤3种情感，各类之间区分特性良好，平均分类正确率为94.4 。其中分类器采用混合高斯分布模型。-The system of speech emotion recognition
main_yuyinzuhe
- 本程序是讲多段语音组合为一段长语音方便进行处理，尤其是在需要进行噪声混合之列的情况-This program is about the combination of multi-stage voice for a long speech to facilitate handling, especially in the need for columns of noise mixed case
kengfen_v51
- 旋转机械二维全息谱计算，利用贝叶斯原理估计混合logit模型的参数，语音信号的采集与处理，数字信号处理课设。- Rotating machinery 2-d holographic spectrum calculation, Bayesian parameter estimation principle mixed logit model, Acquisition and Processing of the speech signal, digital signal processing cla
quzao
- 去噪 风声去噪 人声分离：将已混合的不同的声音分离开(reduce noise separate different voice)
SR
- WinForm界面，实现实时的离线中英文混合语音识别。速度很棒，识别率有待提高。(WinForm interface for real-time offline mixed speech recognition in Chinese and english. The speed is great, and the recognition rate needs to be improved.)
盲源分离
- 盲源分离来实现混合语音的分离，对于学习语音信号的有着很好的参考作用(Blind Source Separation (BSS) is a good reference for learning speech signals.)