-
psola
psola算法的设计与实现，经过调试已经可以运行(psola Algorithm Design and Implementation, after debugging has to run)
- 2007-10-16 11:42:05下载
- 积分：1
-
L1General
Maltlab program for Compressive sensing using L1 minimization
- 2018-01-08 22:46:44下载
- 积分：1
-
sfs310s1
SFS提供了计算语音本质的一系列工具。包括支持各种数据格式，信号处理和图形，频谱、共振峰分析，基频提取等等。在线文档说明请访问http://www.phon.ucl.ac.uk/resource/sfs/help/(SFS provides a voice calculated nature of a series of tools. Including support for various data formats, signal processing and graphics, spectrum, formant analysis, frequency, etc. extraction. Online document shows, please visit http :// www.phon.ucl.ac.uk/resource/sfs/help/)
- 2007-04-03 14:54:52下载
- 积分：1
-
matlab_shuziyuyin
本次课程设计主要介绍了语音信号的录制、语音信号的采集与分析、语音信号的采样、语音信号的频谱分析、加噪后的频谱分析、滤波器的设计以及对于语音信号的回放等知识。通过 Cool Edit录制一段语音信号，运用MATLAB对其进行时域与频域分析，然后设计滤波器加入噪声进行滤波处理，比较滤波前后始于波形或频谱的变化，最后实现对于语音的回放设计。(Digital voice processing filter design)
- 2020-12-22 16:19:07下载
- 积分：1
-
PVVSSessP2Po
语音通信控件源码点对点专用版简介VSession语音通信控件源码点对点专用版，版本2.0，此版本集成了G729A压缩算法，实时传输协议，话音清晰流畅！使用简单易懂方便！此控件源码是在本人以前发布的控件件源码VSessionn2.0版本的基础上，加入点对点通信时的呼叫，应答，挂断等通话前后的同步功能，使其用于点对点通信更加方便！如果您想要在程序源码中自定义点对点间的通话联系方式，或者有一对多，多对多的
(Voice communications control source peer-to-peer special edition Introduction VSession voice communication control source peer-to-peer special edition, version 2.0, this version integration the G729A compression algorithm, Real-time Transport Protocol, clear and smooth voice! Easy to understand and easy to use! This control source is in the I control previously released the parts source VSessionn2.0 version based on peer-to-peer communication call, answer, hang up, etc. the synchronization function before and after the call to make it more convenient for point-to-point communication ! If you want to program source from the definition of point-to-point calls between Contact, or one-to-many, many-to-many)
- 2012-09-15 22:00:40下载
- 积分：1
-
speech-enhancement-
语音增强算法，基于人耳听觉掩蔽的维纳滤波(Subspace speech enhancement algorithm based on human auditory masking Wiener filter)
- 2015-07-19 13:17:44下载
- 积分：1
-
GMM
GMM说话人识别平台全套，从特征提取到模式识别，到识别率，一整套都有(GMM speaker recognition platform full, from feature extraction to pattern recognition, the recognition rate, set both)
- 2013-07-20 19:01:49下载
- 积分：1
-
segSNR+IS
提供了segmantal SNR及IS的计算代码，用于语音增强后评价用。(Provided segmantal SNR and IS calculation code for speech enhancement with post-evaluation.)
- 2020-07-13 09:38:52下载
- 积分：1
-
banhui
完整的基于HMM的语音识别系统，时间序列数据分析中的梅林变换工具，最终的权值矩阵就是滤波器的系数。( Complete HMM-based speech recognition system, Time series data analysis Mellin transform tool, The final weight matrix is ??the filter coefficient.)
- 2016-12-06 09:45:06下载
- 积分：1
-
171724210736171
MFCC：Mel频率倒谱系数的缩写。Mel频率是基于人耳听觉特性提出来的，它与Hz频率成非线性对应关系。Mel频率倒谱系数(MFCC)则是利用它们之间的这种关系，计算得到的Hz频谱特征。(Speech signal feature extraction)
- 2018-05-08 17:47:13下载
- 积分：1
