基于最小均方误差对数谱幅度估计的心音降噪算法-《中国医学物理学杂志》

文章信息/Info

Title:: Heart sound denoising algorithm based on minimum mean-square error log-spectral amplitude estimation

作者:: 冯帅1; 刘飞飞2; 伍昕宇2; 3; 张建文1; 刘子由4; 李嘉豪5; 1.江西理工大学机电工程学院，江西赣州 341000； 2.江西理工大学电气工程与自动化学院，江西赣州 341000； 3.上海博瑟特智能科技有限公司，上海 200000； 4.赣南医学院第一附属医院心脏大血管外科，江西赣州 341000； 5.赣州职业技术学院汽车工程系，江西赣州 341000

Author(s):: FENG Shuai1; LIU Feifei2; WU Xinyu2; 3; ZHANG Jianwen1; LIU Ziyou4; LI Jiahao5; 1. School of Mechanical and Electrical Engineering, Jiangxi University of Science and Technology, Ganzhou 341000, China 2. School of Electrical Engineering and Automation, Jiangxi University of Science and Technology, Ganzhou 341000, China 3. Shanghai PULSATE Technology Co., Ltd, Shanghai 200000, China 4. Department of Cardiovascular Surgery, First Affiliated Hospital of Gannan Medical University, Ganzhou 341000, China 5. Department of Automotive Engineering, Ganzhou Polytechnic, Ganzhou 341000, China

Keywords:: Keywords: heart sound denoising minimum mean-square error log-spectral amplitude heart sound classification electronic stethoscope

摘要:: 将基于最小均方误差对数谱幅度估计的语音增强算法用在心音降噪中，该方法基于统计模型方法将降噪归于统计框架中，通过对带噪心音信号进行最优幅度谱估计，最小化估计心音与干净心音的差异来去除噪声，恢复原始的信号。实验结果表明，本文算法有效改善了心音信号的时频特征，并在后续的心音分类算法中获得了更高的准确率。本文方法在心音降噪中表现优秀，对电子听诊器、心脏病自动检测技术的发展具有重要意义。

Abstract:: Abstract: The study is the first to apply a speech enhancement algorithm based on minimum mean-square error log-spectral amplitude estimation in heart sound denoising. Based on statistical modeling, the denoising is incorporated into a statistical framework. Through the optimal amplitude spectrum estimation on noisy heart sound signals, the difference between estimated and clean heart sounds is minimized to remove noise and restore the original signals. The experimental results show that the proposed algorithm can effectively improve the time-frequency characteristics of heart sound signals and achieve higher accuracy in subsequent heart sound classification. The excellent performance of the proposed method in heart sound denoising is of great significance for the development of electronic stethoscopes and automatic heart disease detection technology.