| 多带谱相减结合感觉加权的语音增强方法研究 |
| |
| 引用本文： | 王晓娣.多带谱相减结合感觉加权的语音增强方法研究[J].电力系统通信,2005,26(12):50-53. |
| |
| 作者姓名： | 王晓娣 |
| |
| 作者单位： | 南京邮电大学,通信工程系,江苏,南京,210003 |
| |
| 摘 要： | 语音增强技术是解决噪声污染的一项强有力的预处理技术,也是语音信号处理的一个热门课题.文章提出了一种多带谱相减与感觉加权相结合的语音增强方法.该方法首先对带噪语音进行多带谱相减,然后根据人的听觉掩蔽特性,对多带谱相减后的信号进行感觉加权,以便进一步降低背景噪声.仿真结果表明,该方法在较好地抑制背景噪声和残留音乐噪声的同时,保持了较好的语音可懂度.
|
| 关 键 词： | 语音增强 多带谱相减 感觉加权 听觉掩蔽特性 |
| 文章编号： | 1005-7641(2005)12-0050-04 |
| 收稿时间： | 2005-06-08 |
| 修稿时间： | 2005年6月8日 |
Speech enhancement method based on multi-band spectral subtraction plus perceptual weighting |
| |
| WANG Xiao-di.Speech enhancement method based on multi-band spectral subtraction plus perceptual weighting[J].Telecommunications for Electric Power System,2005,26(12):50-53. |
| |
| Authors: | WANG Xiao-di |
| |
| Abstract: | The pronunciation-strengthened technology is a powerful treatment technology for solving the noise pollution;it is also a hot subject in voice signal processing.In this paper a speech enhancement method based on multi-band spectral subtraction plus the perceptual weighting algorithm has been put forward,this method can suppress noise.Firstly,this method performs multi-band spectral subtraction,and then based on the acoustical masking characteristics of human auditory system a processing of weight to feeling is brought to bear upon the subtracted signals.The simulation results show that the method has excellent performance in background noise and "remnant music noise" suppression,and at the same time the speech signal keeps very low audible distortion. |
| |
| Keywords: | speech enhancement multi-band spectral subtraction perceptual weighting acoustical masking characteristics |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
