Weiyang Cai

Learn More
Fundamental frequency (<i>F</i><inf>0</inf>) is one of the essential features in many acoustic related applications. Although numerous <i>F</i><inf>0</inf> detection algorithms have been developed, the detection accuracy in noisy environments still needs improvement. We present a hybrid noise resilient <i>F</i><inf>0</inf> detection algorithm named BaNa(More)
Thresholding is a simple but effective technique for image segmentation. In this paper, a novel method is presented to address the problem of image segmentation for uneven lighting images that is based on dynamic size of window. In pyramid approach (window merging), segmentation accuracy depends on the initial size selection. The proposed method is based on(More)
Acoustic feature extraction algorithms play a central role in many speech and music processing applications. However, noise usually prevents acoustic feature extraction algorithms from obtaining the correct information from speech and music signals. Thus, the robustness of acoustic feature extraction algorithms is an area worth studying. In this thesis, we(More)
  • 1