基于改进小波阈值和优化VMD算法的语音增强方法  

Speech Enhancement Method Based on Improved Wavelet Threshold and Optimized VMD Algorithm

作　　者：张礼艳 刘增力[1] 彭艺[1] ZHANG Liyan;LIU Zengli;PENG Yi(Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650500,China)

机构地区：[1]昆明理工大学信息工程与自动化学院,昆明650500

出　　处：《吉林大学学报(理学版)》2025年第2期608-621,共14页Journal of Jilin University:Science Edition

基　　金：国家自然科学基金(批准号:61761025)。

摘　　要：针对语音信号传输过程中受噪声和回声等因素干扰,导致信号质量和可懂度下降的问题,提出一种基于优化的变分模态分解算法和改进小波阈值的语音信号增强方法.首先,采用麻雀搜索算法优化模态分解参数,并分解语音信号得到模态分量;其次,根据模态分量与原信号的相关系数和中心频率,消除高频噪声分量,保留接近原信号的模态分量作为纯语音,其他模态分量作为带噪语音,进行小波阈值处理;最后,重构纯语音和处理后的噪声模态分量,得到增强的语音信号.结果表明:该方法比单一方法具有更优的语音增强效果;优化的变分模态分解算法和改进的阈值与阈值函数实现了比传统方法更好的增强效果,适用于各种噪声环境,有效提升了语音信号的质量和可懂度.Aiming at the problem that noise,echo and other factors interfered with the quality and intelligibility of the s ignal in the process of speech signal transmission,we proposed a speech signal enhancement method based on optimized variational mode decomposition algorithm and impr oved wavelet threshold.Firstly,the modal decomposition parameters were optimized by using sparrow search algorithm,and the modal components were obtaine d by resolving the speech signal.Secondly,according to the correlation coefficient and center frequency between the modal component and the original signal,the high-frequency noise component was eliminated,and the modal component close to the original signal was retained as pure speech,while the other modal components were r egarded as noisy speech,and the wavelet threshold processing was carried out.Finally,the pure speech and the processed noise modal components were reconstructed t o obtain the enhanced speech signals.The results show that the method has better speech enhancement effect than a single method,the optimized variational mode decompos ition algorithm and the improved threshold and threshold function achieve better enhancement effect than the traditional methods,which is suitable for al l kinds of noise environment,and effectively improve the quality and intelligibility of speech signals.

关 键 词：语音增强 麻雀搜索算法 变分模态分解 小波阈值 相关系数 

分 类 号：TN912.35[电子电信—通信与信息系统]