摘要
在传统谱减法语音增强的基础上,针对不同性别带噪语音信号采用传统的谱减法后残余音乐噪声过强的问题,提出采用被减项加权处理和功率谱修正处理相结合的改进方法,采取Matlab实验仿真分析,实验结果表明,该方法降低了音乐噪声,改善了语音信号的输出信噪比,达到了抑制纯音噪声的目的。
On the basis of the traditional speech subtraction speech enhancement,for the different sex noisy speech signal using the traditional spectral subtraction residual music noise is too strong problem,An improved method of combining weighted weighting and power spectrum correction processing is proposed,taking Matlab simulation and analysis.It was showed that the experimental results reduce the noise of the music and improve the output signal to noise ratio of the speech signal,and achieve the purpose of suppressing the pure tone noise.
出处
《青岛大学学报（自然科学版）》
CAS
2017年第3期25-28,共4页
Journal of Qingdao University(Natural Science Edition)
基金
青海省2016重大科技专项计划(批准号:2016-NN-142)资助
