基于LMS的语音信号去噪算法

语音是人们进行思维沟通交流的主要桥梁，语音通信处理在现实环境下会受到各种各样的干扰，从受干扰的语音中尽可能地去除噪声，提高语音质量，是目前现代信号处理领域中至关重要的技术之一。引入了LMS自适应滤波法，并提出了变步长的LMS，同时实现了小波阈值降噪和LMS结合的自适应噪声对消。并选用不同的男声和女声语音，录制真实环境下的非平稳噪声，仿真实验表明小波阈值结合LMS的噪声对消法去噪性能最好，大幅提高了信噪比，改善了语音质量。

voice signal Removal Noise Based on LMS Algorithm

Voice is the main bridge for people to communicate with each other.Voice communication processing in the real world will be subject to a variety of interference, from the interference of voice as much as possible to remove noise and improve voice quality, is the field of modern signal processing is one of the most important technology.The LMS adaptive filtering method is introduced, and a variable step size LMS is proposed, and the adaptive noise cancellation of wavelet threshold noise reduction and LMS combining is realized.The simulation results show that the wavelet threshold combined with the noise of LMS is the best, and the signal - to - noise ratio is improved greatly, and the speech quality is improved by using the sound of different male and female voice.