Window Function Dependency on Male and Female Speech Signals for Pitch Extraction at Low SNRs

This research suggests an efficient idea that is better suited for speech processing applications for retrieving the accurate pitch from speech signals in noisy conditions. Almost every pitch detection method has windowing as a significant part of segmentation. This research considers using Hanning, Hamming, and rectangular windows’ function on male and female speech signals separately for pitch extraction. Also, analyze the windowing effect on the speech signal analytically to understand which window function is more suitable and effective for male and female speech signals specifically. For the validation of our idea, we have utilized the conventional autocorrelation function, cepstrum method and state-of-the-art method BaNa. This study puts out a potent idea that will work better for speech processing applications in noisy speech. From experimental results, the proposed idea represents which window function is more appropriate for male and female speech signals in noisy environments.