Pitch Extraction Based on Weighted Autocorrelation Function in Speech Signal Processing

It is very difficult to determine the accurate pitch in speech signal processing. For overcome the problem, a new method of weighted pitch detection which based on autocorrelation function is proposed in this paper, Firstly, because the method of average magnitude difference function has similar characteristics with the autocorrelation function, on the basis of autocorrelation function, we use the square of the reciprocal of the average magnitude difference function as a weight coefficient. In the end, we obtain the new algorithm of pitch extraction. Moreover, the pitch contour is smoothed in order to obtain better effect. Simulated experimental results show that the new algorithm can perform pitch detection. In addition, it also improves the accuracy of pitch detection.