Description: In order to improve voice activity detection (VAD) in low SNR (10 dB) accuracy under proposed based on short-time fractal dimension of the improved algorithm. Combined with the characteristics of the speech signal, to 2 commonly used fractal dimension of speech signals are compared and calculated choice to follow the same dynamic endpoint threshold adaptive detection of voice. The results showed that: 6 ~ 10 dB for the signal to noise ratio of noisy speech, this method can detect the entire speech, but has some noise robustness, the system can be adaptively adjusted during operation to adapt to environmental noise threshold of changes to improve the accuracy of VAD algorithms. This is the source matlab.
To Search:
- [asdfasdfsad] - In the VC environment to achieve the inp
File list (Check if you may need any files):
分形\changdu.wav
....\corr_integral.m
....\fenxingtest.m
....\FractalDim.m
....\GP_CD.m
....\heaviside.m
....\test.wav
分形
Download