Welcome![Sign In][Sign Up]
Location:
Search - fdpsola

Search list

[Speech/Voice recognition/combinefdpsola

Description: 语音合成程序!psalo频域基音同步叠加方法。它首先对原始语音信号进行短时频域变换,得到短时谱和短时谱包络。短时谱除以短时谱包络得到声源短时谱,对声源短时谱的实部和虚部分别进行线性插值,就可以达到改变语音信号基频的目的,然后再进行频域反变换,可得到变换后的短时语音信号。短时谱包络部分也可以独立改变,以达到改变音色的目的。-speech synthesis procedures! Psalo frequency domain pitch synchronous superposition method. It is first of the original speech signal for short-time frequency domain transform, to be short-term and short-term spectral envelope spectrum. Short-term spectrum divided by the short-time spectral envelope of the sound source to be short-term spectrum of the sound spectrum of short-term real and imaginary parts of linear interpolation, they could change the voice-frequency signals to the end, then we will proceed to frequency-domain transform, Transform available after the short speech signal. Short-term spectral envelope can be independent of changes to achieve the objective of changing colors.
Platform: | Size: 2553 | Author: hzh | Hits:

[Speech/Voice recognition/combinefdpsola

Description: 语音合成程序!psalo频域基音同步叠加方法。它首先对原始语音信号进行短时频域变换,得到短时谱和短时谱包络。短时谱除以短时谱包络得到声源短时谱,对声源短时谱的实部和虚部分别进行线性插值,就可以达到改变语音信号基频的目的,然后再进行频域反变换,可得到变换后的短时语音信号。短时谱包络部分也可以独立改变,以达到改变音色的目的。-speech synthesis procedures! Psalo frequency domain pitch synchronous superposition method. It is first of the original speech signal for short-time frequency domain transform, to be short-term and short-term spectral envelope spectrum. Short-term spectrum divided by the short-time spectral envelope of the sound source to be short-term spectrum of the sound spectrum of short-term real and imaginary parts of linear interpolation, they could change the voice-frequency signals to the end, then we will proceed to frequency-domain transform, Transform available after the short speech signal. Short-term spectral envelope can be independent of changes to achieve the objective of changing colors.
Platform: | Size: 2048 | Author: hzh | Hits:

[Speech/Voice recognition/combinetdpsolamatlab

Description: 此程序在matlab环境下运行,是完整的tdpsola和fdpsola程序,包含了前期的语音读入,预处理,清浊音判决等等很全面-This procedure to run in matlab environment, is a complete program tdpsola and fdpsola include pre-read the speech, pre-processing, audio Qingzhuo comprehensive judgments, etc.
Platform: | Size: 13312 | Author: junyizhang | Hits:

CodeBus www.codebus.net