资源列表
Td-psolaPitchDuration
- 使用TD-PSOLA(td-psola、psola)算法,做了一个语音合成,实现语音声调的变调,时长的变化等功能。参考praat源码,提取出其合成方法,效果不错。需要提供pitchtier、durationtier、pointprocess等准换信息文本(可由praat产生)供readfile函数读入-Use TD-PSOLA (TD-PSOLA, PSOLA algorithm, made a speech synthesis, speech tone tone sandhi, long-te
kernel-linear-principal-componenet
- this principle component analysis(PCA) that is used for linear dimensionality reduction and feature extraction as well as the nonlinear form of PCA which is KPCA and how PCA is used for Active shape models -this is principle component analysis(PCA) t
5
- 对语音信号进行信噪比计算,对语音信号进行加噪声处理,然后进行消噪处理计算信噪比。-Speech signal is processed by the signal to noise ratio, and the speech signal is processed by adding noise, and the signal to noise ratio is calculated.
yuyinduandianjiance
- 语音端点检测算法,采用双门限判别法,代码包括很多调用函数和实验语音,可以实现。-Speech endpoint detection algorithm, using double threshold discrimination method, the code includes many function calls and experimental phonetics, can achieve.
luyindaima
- matlab 软件实现播放并复读播放的语音实现录音功能并保存录音-The MATLAB software and the realization of voice broadcast repeat playback recording and save the recording
SpeakerRecognition
- speaker recognition process (MFCC + VQ)
pingjie
- 波形拼接,利用相关系数平滑拼接波形 用来语音合成的平滑处理-Waveform concatenation, using the correlation coefficient of smooth to stitch waveform
DTW_V_1_0
- 动态世间规整(DTW)jar包,里面包含了所有包括特征提取mfcc fft enframe 等所有功能,只需输入语言路径即可-Dynamic world of regular (DTW) jar package, which contains all the features extracted include all the features of mfcc fft enframe etc., just enter the path to the language
TTS_tools
- 调用灵云的TTS库,实现文本和语音的转换, 云端调用,免费使用,该程序可以做为本地TTS转换工具使用,简单灵活,也可以在其基础上稍做修改,做成TTS网关程序,用在呼叫中心平台上 -Strato s TTS library calls, text and voice conversion, Cloud calls, free use of the program can be used as a local TTS conversion tools to use, simple a
duandian_test2
- 一个基于matlab 的语音端点检测程序,对于语音识别来说比较有用.-Matlab based speech endpoint detection procedures, it is useful for speech recognition.
MusicRecogniseding
- 国科大数字信号处理2课程,基于Python的哼唱识别,有乐库的-ucas digital signal processing 2 courses, humming recognition based on Python, there is music library
pageturner
- 自动乐章翻页 音乐信号处理。This code implements a basic function to turn musical notes page automatically by comparing the real-time musical signal with the pattern which is made in advance. -Automatic Page Turner.