图形用户界面下敏感语音提取的仿真实现  

The simulaiton of sensitive speech extraction based on GUI

作　　者：张学敏[1] 王秀艳[1] 张建红[1] 

机构地区：[1]长春工程学院电气与信息工程学院,长春130012

出　　处：《长春工程学院学报（自然科学版）》2011年第2期109-112,共4页Journal of Changchun Institute of Technology：Natural Sciences Edition

摘　　要：获取纯净语音的不同频段音效时,常存在提取方法复杂、数据修改麻烦及效果不直观的缺点。鉴于此,利用短时傅里叶变换获取纯净语音在频域的频谱特性并分析其频谱分布特点,采用不同类型的FIR数字滤波器对纯净语音的感兴趣区进行敏感语音的提取,从而产生低音、中音和高音音效,并通过MATLAB图形用户界面实现之。仿真结果表明:在不同频段进行的敏感语音提取音效明显,声音感染力强。同时,利用图形用户界面实现敏感语音的提取具有数据修改方便、操作简单灵活、效果直观明了的优点。There are always some defects in obtaining sound effect of pure speech in different frequency section,such as the complicated extraction,inconvenient data modification and non-intuitive effect.So this paper tries to apply the feature of using short time fourier transform to gain pure sound in frequency zone to analysis the characteristics of frequency distribution.It makes a sensitive speech extraction to the interested zone of pure sound with different FIR digital filters.Thus the sound effects of bass,midrange and treble are produced,then realized by Graphic User Interface（GUI） of Matlab.The simulation results show that：the effect of sensitive speech extraction in different frequency section is obvious,and with strong sound attraction.Meanwhile the sensitive speech extraction by using GUI has the advantages of convenient data modification,simple and flexible operation,intuitive and clear effects.

关 键 词：短时傅里叶变换 数字滤波器 敏感语音提取 图形用户界面 

分 类 号：TP911[自动化与计算机技术]