搜索资源列表
HMM_HTK-3.0
- 语音识别经典工具HMM_HTK，是语音识别专业工作者的必备研究工具，当今世界上几乎所有的语音识别系统都是以此为基础建立的-classical voice recognition tools HMM_HTK, voice recognition is a prerequisite professionals research tools, in today's world almost all the voice recognition systems are as a basis for
LPCshare
- 语音信号处理，其中A/B Tool可以提供语音文件的‘A/B’比较，详情请见文件夹‘abtool_1.2 中的’readme文件，其中详细描述了该程序包可以实现的功能。可以免去手工编写同样功能代码的麻烦。还请站长审核！期待您的通知！-voice signal processing, A / B Tool can provide voice document 'A / B', see details folders' abtool_1.2 the 'readme f
lpcrr2am
- 用MATLAB来实现声音信号处理的函数程序的源代码。-MATLAB to achieve voice signal processing function of a program's source code.
midi2frq
- 用MATLAB来实现声音信号处理的函数程序的源代码-MATLAB to achieve voice signal processing function of a program's source code
readcnx
- 用MATLAB来实现声音信号处理的函数程序的源代码-MATLAB to achieve voice signal processing function of a program's source code
writehtk
- 用MATLAB来实现声音信号处理的函数程序的源代码-MATLAB to achieve voice signal processing function of a program's source code
rsfft
- 用MATLAB来实现声音信号处理的函数程序的源代码-MATLAB to achieve voice signal processing function of a program's source code
vqonMatlab
- 在MATLAB环境下实现基于矢量量化的说话人识别系统。在实时录音的情况下，利用该说话人识别系统，对不同的人的1s～7s的语音进行辨识。实现与文本无关的自动说话人确认的实时识别。 使用说明： 1 训练 打开Matlab 使Current Directory为VQ所在的文件夹(比如：E:\\vq) 在Command windows中输入 -in MATLAB environment based VQ Speaker Recognition System. Real-
tts.tar
- XChat TTS scr ipt is an perl written XChat2 scr ipt that speaks out messages in irc channels, and more. It provides an interface to setup the functions or view the online help. -XChat TTS is an perl scr ipt written XChat2's at 5 that speaks out m
addhead
- 给无头的语音文件添加头，可以自己定义，添加的市标准的RIFF格式的头-without a head to the paper added voice, who can own definition, add to the city's standards for the first RIFF format
yycl
- 提取语音信号的lpc参数并进行时间归整，需要将wav语音文件放在指定目录下‘e:\\yyzl’-voice signal from the lpc parameters and time consolidation, need to wav sound files on the specified directory 'e : \\ yyzl'
DesignLyonFilters
- Design the cascade of second order filters and the front filters (outer/middle and compensator) needed for Lyon s Passive Short Wave (Second Order Sections) cochlear model.-the cascade of second order filters and the front filters (outer / middl
pocketsphinx-0.2.1.tar
- 这个版本是用于PDA的嵌入式SPHINX版本，针对定点等作了优化，运行速度比较快，当然识别精度肯定难以同sphinx3相提并论，但可以在当今主流PDA上实现实时识别也是相当不错的成绩了-this version for the PDA version Embedded SPHINX against sentinel gave optimization, faster operation speed, of course, it is difficult to identify with prec
HTK3.4forWindows
- HTK3.4是由英国剑桥大学2006年12月推出的最新版本HMM Toolkit, 是世界上流传最广的强大的语音识别的开放源码。如果你遇到什么问题欢迎来http://asr.blog.hexun.com/留言。我们乐于讨论语音识别以及其他模式识别问题。-HTK3.4 from the University of Cambridge, England in December 2006 launched the latest version of HMM Tool kit, is the world
ma_by
- The Matlab functions and scr ipts in the MA toolbox are: - ma_sone wav (PCM) to sone (specific loudness sensation) - ma_mfcc wav (PCM) to MFCCs (Mel Frequency Cepstrum Coefficients) - ma_sh sone to Spectrum Histogram - ma_ph sone to
jiben lms deyanjiu yu fangzhenfenxi
- 基本lms算法的分析研究与方针 是硕士论文 发表于中国学术刊物-basic algorithm research and policy analysis of the master's thesis published in academic journals in China
MSTTSSpeech
- 用微软的ＴＴＳ做的。 用户可以自己安装语音库！-use Microsoft's TTS do. Users can install their own voice library!
potsband
- The routine potsband calculates a bandpass filter corresponding to the standard telephone passband-potsband calculates a bandpas 's filter corresponding to the standard telepho ne passband
Serialization00100
- C#序列化，一个上传测试，没用什么实际功能，请不要下载-sequence, an upload test, it's useless what the actual function, please do not download
mfcc-extraction
- 语音识别中的mfcc参数提取程序，从HTK中剪出来的，结果和HTK得出来的一模一样（配置文件已给）。39维的，带能量。-mfcc extraction process.Come from the HTK