首页 | 本学科首页   官方微博 | 高级检索  
     

改进的基于听觉掩蔽特性的语音增强
引用本文:马义德,邱秀清,陈昱莅,刘映杰,朱敬锋. 改进的基于听觉掩蔽特性的语音增强[J]. 电子科技大学学报(社会科学版), 2008, 0(2)
作者姓名:马义德  邱秀清  陈昱莅  刘映杰  朱敬锋
作者单位:兰州大学信息科学与工程学院;兰州大学信息科学与工程学院 兰州;
基金项目:国家自然科学基金(60572011); 985特色项目(LZ985-231-58262)
摘    要:该文利用人耳感知的掩蔽特性,研究了一种改进的基于人耳听觉掩蔽特性的语音增强方法。该方法改进了对含噪语音中噪声的估计,即在估计噪声时,先在帧上判断语音的有无,然后在频率点上判断语音的有无,最后再从感知的角度,利用估计出的语音信号计算掩蔽阈值,以此在时域和频域上合理地调整增强系数。仿真结果表明,该方法不仅使信噪比有较大的提高,而且减少了语音失真,同时也很好地抑制了背景噪声和残余音乐噪声。

关 键 词:听觉掩蔽  噪声估计  减谱算法  语音增强  

An Improved Method for Speech Enhancement Based on Human Auditory Masking Properties
MA Yi-de,QIU Xiu-qing,CHEN Yu-li,LIU Ying-jie,, ZHU Jing-feng. An Improved Method for Speech Enhancement Based on Human Auditory Masking Properties[J]. Journal of University of Electronic Science and Technology of China(Social Sciences Edition), 2008, 0(2)
Authors:MA Yi-de  QIU Xiu-qing  CHEN Yu-li  LIU Ying-jie     ZHU Jing-feng
Affiliation:MA Yi-de,QIU Xiu-qing,CHEN Yu-li,LIU Ying-jie,, ZHU Jing-feng (School of Information Science & Engineering,Lanzhou University Lanzhou 730000)
Abstract:This paper suggests an improved speech enhancement method based on human auditory masking properties. In this method,an improved noise estimation algorithm is used,then,the estimated results can be used to compute the masking threshold of the speech,after that,the coefficients of time and frequency are adjusted according to perception. The results show that the improved method leads to better signal to noise ratio,significant reduction of background noise,and unnatural structure of the residual noise.
Keywords:auditory masking  noise estimate  spectral subtraction algorithm  speech enhancement  
本文献已被 CNKI 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号