搜索资源列表
mpsound
- 录制一段个人自己的语音信号。对录制的信号进行采样；画出采样后语音信号的时域波形和频谱图；对语音信号进行加噪和去噪处理，画出滤波后信号的时域波形和频谱，并对滤波前后的信号进行对比，分析信号的变化；回放语音信号；实现快录慢放、慢录快放等功能。-Record a person' s own voice signal. Of the recorded signal sampling draw sample after the speech signal time-domain waveform
Speech-processing
- 原创，语音合成matlab程序，可改变一段语音的音调，语速等，实现男声变女声，女声变男声等功能。-The original speech synthesis matlab program can change a voice tone, speed, etc., to achieve male changed Girls, female become male functions.
VBSPEECH
- 里面含有VB代码的，语音识别源码，语音的识别模拟-Which contains the VB code, speech recognition source code, speech recognition Simulation
detection
- 基于倒谱，分形，和谱熵的语音端点检测程序，三个文件夹内对应三种程序-Cepstrum-based, fractal, and spectral entropy of speech endpoint detection procedures, the three folders corresponding to the three procedures
msttss22L
- 微软 text to speech 4.5引擎-Microsoft text to speech 4.5 engine
kalman
- 该程序是卡曼滤波法在语音处理上的应用,能有效的去除噪声,达到语音增强的目的!-The program is Kaman filtering method in the voice processing application, can effectively remove the noise, to achieve the purpose of speech enhancement!
CRF1-2
- CRF1.2，条件随机场软件包，很好用很流行的一个文本分类软件，可以用于自然 语言的处理，标签，分类，词性发现，用户只需要着重构造特征函数既可以，实验结果和应用表明crf要优于隐马尔科夫模型。实现环境为java语言。-CRF1.2, conditions package with the airport, very good very popular with a text classification software, can be used in natural language proc
Subspacealgorithm
- 子空间算法是语音增强中较新颖的算法，文件对该算法进行了仿真-Subspace method is relatively new in the speech enhancement algorithm, the algorithm was simulated file
Burg
- 实现两个语音信号的分离，采用Burg算法-To achieve the separation of two speech signals using the Burg algorithm
MMSE
- 最小均方误差估计（MMSE）语音增强算法，算法简单有效，无残余音乐噪声-Minimum mean square error estimation (MMSE) speech enhancement algorithm is simple and effective, non-residual musical noise
dwt
- 基于动态时间规划（DTW）的语音信号识别，MATLAB环境下的-Dynamic Programming (DTW) of the speech signal recognition, MATLAB environment
LIONSKY.NET
- 利用微软提供的speech SDK，用C#实现的简单语音识别系统。-The use of Microsoft' s speech SDK, to use C# to achieve a simple voice recognition system.
SpeechPLib(2004.11)
- 基于微软speech sdk 的中文语音识别-Chinese Recognition based on MIcrosoft SDK
gmmem_several
- GMM是语音识别中比较成熟的算法之一，这个MATALB完整的实现了基于GMM算法的识别训练程序，可以适用于GMM识别和学习的同行的参考-GMM is a speech recognition algorithm for the more mature one, this MATALB full implementation of the identification algorithm based on GMM training procedures, can be applied to GMM
xingzj0117_SRC_Speech
- delphi基于MS SPEECH 5.1的语音识别演示-delphi-based MS SPEECH 5.1 Speech Recognition Demo
VoiceRecognitionMarkovianMatlab
- 基于马尔科夫链的连续语音识别的源代码Matlab源码--Speech Recognition Matlab source code--
2
- c#中文分词源码,基于词频,词性等,可提取自定义数量的关键词-Chinese word c# source code, based on word frequency, part of speech, can customize the number of keywords extracted
adaptivelms
- 基于小波变换的可变步长自适应LMS语音信号去噪程序，对实际复杂噪声具有很好的效果-Based on wavelet transform adaptive variable step size LMS Speech Signal Denoising procedures, the actual complexity of the effect of noise has a very good
cspeech
- 为微软SAPI(Text-to-Speech API)封装的类- Kind (Text-to-Speech API) seals which for Microsoft SAPI
MMSEpujian
- 这个是语音信号处理里面的基于MMSE的谱减法增强处理程序，此种方法是我见过消除噪声最好的！-This is the speech signal processing inside the MMSE-based spectral subtraction to enhance handling procedures, this method is the elimination of noise, the best I' ve ever seen!