搜索资源列表
EM
- 语音识别对于电脑的智能化要求是比较高的， 它的发展经历了从静态的单个词的识别．特定人的 识别，以及非特定人的识别和动态连续语音的识别 几个历程。在1997年9月4日．IBM 经过26年 的潜心研究，终于向中国市场发布了其语音识别新 产品ViaVoice。这不但提高了汉字输入速度，而且 能使讲话人更自然流畅地表达自己的意图-Speech Recognition requirements for the intelligent computer is relatively h
matlabluying
- MATLAB语音识别的一个源代码，不是很成熟，只能识别英文，实时性比较差，但是能运行，可以做为实验代码和待修改的源代码。-Speech Recognition a MATLAB source code is not very mature, and only recognizes English, real-time is rather poor, but it can run, you can be used as experimental code and modify the source
FIR
- 绘制一段语音信号的波形并观察其频谱，用三角窗设计一个满足给定相应技术指标的FIR滤波器，对该语音信号进行滤波去噪处理，比较滤波前后的波形和频谱并进行分析。
FFT_lowpass
- 采用FFT和低通滤波器的两种语音除噪算法比较，MATLAB编程，附效果图-Using FFT and low pass filter audio noise canceling algorithm for the two compare, MATLAB programming, with a results map
yuyin_fundamental
- 语音信号基本的处理，包括spectrogram和specgram两个函数的比较-The basic speech signal processing, including spectrogram and specgram comparison of the two functions
AudioAecDemo
- 音频聊天的源代码,能够实现语音通话，比较流畅-Audio chat source code, to achieve a voice call, more fluid
baoshi
- C# 语音报时，含有完整的声音资源文件，不过程序好像还有点小毛病，有时候报时会重复，毕竟程序比较复杂，也会报日期，程序运行截图如上所示，点击“报时”按钮即可听到电脑报时间。记得以前发过类似程序，各有各的实现方法，多学习一些总有好处的。 -C# voice timekeeping, with complete sound resource file, but the program seems to have petty problems, sometimes the newspaper wi
yuyinhecheng
- 全面介绍语音合成的知识比较系统很适合语音学习-A comprehensive comparative introduction speech synthesis system is suitable for knowledge language learning
My_Super729
- 比较常用的语音压缩算法superg729，压缩效率高，码流比较低，非常优秀-Voice compression algorithm superg729
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
voice
- 语音加噪程序有两个可以运行比较简单。任何语音即可-Voice plus noise process, there are two, you can run, relatively simple
work
- 对语音信号进行分析,求其能量谱.并与原语音信号进行比较-Analysis of the speech signal, find its energy spectrum. And compare with the original speech signal
HTK-Linux-3.3.tar
- 语音识别源代码，是剑桥大学机器人视觉组开发的。识别效果比较好。-HTK is a toolkit for use in research into automatic speech recognition
-sphinx4
- 一套关于用java编写语音软件的资料，是本人收集的，类似于这种的资料比较少-Prepared a set of voice software with java information is my collection, similar to that less information
HTK-book
- 推荐的HTK 语音识别类的书籍，可以买来看看，有本比较多理论方面的知识-Recommended books like HTK speech recognition, you can buy a look, there is the theory of knowledge more
opensmile-bin-1.0.1
- 一个能进行语音识别的软件源码。是国外开发的。安装比较麻烦-A voice recognition software to source code. Is developed abroad. Too much trouble to install
jidianzantai
- 这是暂态上机的机电部分，这个程序是比较流形普遍的，而且用的编程语音简单易懂-This is the transient electrical and mechanical parts on the machine, this program is more general manifolds, and audio programming using straightforward
xyl
- 语音处理匈牙利算法的实现，比较简单，望大家赐教-Speech processing algorithm implementation in Hungary, a relatively simple, hope you enlighten me
12345.RAR
- 基语音信号处理中的一些算法代码，比较齐全，希望对各位有些帮助- voice signal processing of some computation code, relatively complete, hope to you some help
enframe0613pm
- 语音信号端点检测的程序，比较全面，能量过零率基音估计等等 全在-Endpoint detection of speech signal process, more comprehensive, zero crossing rate of energy and so on all in the pitch estimation