资源列表
SOX
- 今天我给大家介绍一款自称是音频处理界的瑞士军刀的一款开源软件，SoX - Sound eXchange。引用主页上介绍的原话：-Today I introduce a claim to be the Swiss Army knife of audio processing sector, an open source software, SoX- Sound eXchange. References home presentation original words:
capturesound
- capturesound and play sound
WavCompareBYAlbrook
- 音频播放、录制、对比，本动态链接库专用于VFP所调用的16位FLL，由VC 6++所编译。-audio wave play, record, compare, can be called by VFP.
SpeechAddNoise_matlab
- noisegen.m：生成白噪声并按照指定信噪比对语音进行加噪； add_noisem.m：使用输入的噪音按照指定信噪比对语音进加噪； SNR_singlech.m：输入纯净语音和加噪后的语音，计算其信噪比； my_add_noise.m：调用上述函数进行加噪操作；-noisegen.m: white noise generated by the specified signal to noise ratio of the speech plus noise add_noisem.
msapismp
- Delphi调用MS SAPI自由朗读英文的示例程序源代码-Reading English aloud in Delphi call MS SAPI free sample application source code
51Voicerx
- Stc512.4G接受语音播放代码，原创，独家发布-STC51 2.4G rx voice play!
voice
- STC51AD采集2.4G传输语音！绝对原创独家发布-STC51AD voice trans to 2.4GRF
Wave
- 实时采集语音信号；显示语音信号的时域波形；重放采集的语音信号。-Real-time voice signal acquisition display time-domain waveform of the speech signal voice signal reproduction acquisition
enframe
- 对信号进行分帧加窗，只要输入原始信号，帧长，帧移，窗类型即可获得分帧后信号。-To frame and window of the signal, as long as the input of the original signal, frame, frame, window type can obtain after framing signal.
CPPyuyinshibie
- 基于C++语言编写的一个简单的语音识别系统的源代码-Based C++ language a simple voice recognition system source code
MFCCfinal
- 梅尔倒谱系数，用于计算语音信号的特征系数，然后使用这些特征系数对语音信号进行重建-MFCC，one algorithme to calculater the feature of voice signal, ad we can use these features to reconstruct voice signal
speech-recognition
- 基于HMM算法的孤立词，非特定人的语音识别，主要是HMM算法在语音识别上的应用。- HMM-based algorithm, Isolated word，non-specific speech recognition, mainly HMM Algorithm in Speech Recognition.