改进相位补偿结合谐波重构的语音增强方法  

Speech enhancement method for improving phase compensation combined with harmonic reconstruction

作　　者：崔磊 马建芬 张朝霞 CUI Lei;MA Jian-fen;ZHANG Zhao-xia(College of Information and Computer,Taiyuan University of Technology,Jinzhong 030600,China;College of Physics and Optoelectronics,Taiyuan University of Technology,Jinzhong 030600,China)

机构地区：[1]太原理工大学信息与计算机学院,山西晋中030600 [2]太原理工大学物理与光电工程学院,山西晋中030600

出　　处：《计算机工程与设计》2022年第4期949-955,共7页Computer Engineering and Design

基　　金：山西省重点研发计划(高新技术领域)基金项目(201803D121057);山西省回国留学人员科研基金项目(2017-031)。

摘　　要：为解决传统单声道语音增强方法在对相位处理时存在的不足以及降噪过程中普遍存在的语音失真问题,提出改进相位补偿结合谐波重构的语音增强方法。通过深度学习模型估计先验信噪比并利用先验信噪比对传统相位谱补偿(PSC)函数进行改进,针对在降噪过程中出现的语音失真问题,对增强后的语音通过谐波重构进行二次增强。实验结果表明,改进相位补偿结合谐波重构的语音增强方法较对比方法具有更好的降噪能力,可以有效减少语音失真,提高语音质量。To solve the shortcomings of traditional monophonic speech enhancement method in the phase processing and the common speech distortion problem in the denoising process,a speech enhancement method with improved phase compensation combined with harmonic reconstruction was proposed.A priori signal-noise-ratio(SNR)was estimated using deep learning model and the traditional phase spectral compensation(PSC)function was improved using the priori SNR,aiming at the speech distortion problem occurred in the denoising process,the enhanced speech was secondarily enhanced by harmonic reconstruction.Experimental results show that the proposed method has better denoising capability than the comparison method,which can effectively reduce speech distortion and improve speech quality.

关 键 词：先验信噪比 语音增强 相位优化 深度学习 维纳滤波 谐波重构 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]