An Improved Time Domain Pitch Detection Algorithm for Pathological Voice | Science Publications

American Journal of Applied Sciences

Ahmad K.A. Ibrahim¹  Kartini Ahmad¹  Mohd R. Jamaludin¹  Kamarulafizam Ismail¹  Tan T. Swee¹  Sheikh H.S. Salleh¹ 

关键词: Pitch Detection Algorithm (PDA);    dysphonia;    autocorrelation;    Merged Normalized Forward Backward Correlation (MNFBC);    pathological voices;    Hilbert-Huang Transform (HHT);    time domain;    mean error;    Auto Correlation Function (ACF);   

DOI  :  10.3844/ajassp.2012.93.102

学科分类：自然科学（综合）

来源: Science Publications

【 摘 要 】

Problem statement: The present study proposes a new pitch detection algorithm which could potentially be used to detect pitch for disordered or pathological voices. One of the parameters required for dysphonia diagnosis is pitch and this prompted the development of a new and reliable pitch detection algorithm capable of accurately detect pitch in disordered voices. Approach: The proposed method applies a technique where the frame size of the half wave rectified autocorrelation is adjusted to a smaller frame after two potential pitch candidates are identified within the preliminary frame. Results: The method is compared to PRAATs standard autocorrelation and the result shows a significant improvement in detecting pitch for pathological voices. Conclusion: The proposed method is more reliable way to detect pitch, either in low or high pitched voice without adjusting the window size, fixing the pitch candidate search range and predefining threshold like most of the standard autocorrelation do.

【 授权许可】

Unknown