| 基于拉普拉斯模型和掩蔽效应的语音增强 |
| |
| 引用本文： | 徐翠香,马建芬.基于拉普拉斯模型和掩蔽效应的语音增强[J].计算机工程与应用,2010,46(7):153-154. |
| |
| 作者姓名： | 徐翠香 马建芬 |
| |
| 作者单位： | 太原理工大学计算机与软件学院,太原,030024 |
| |
| 摘 要： | 提出了一种有效的消除噪声且减小语音失真的语音增强方法。首先实现了语音信号服从Laplacian分布、噪声服从Gaussian分布假设下的MMSE增强算法。为了进一步提高语音增强效果，在增强语音谱幅度阈值的计算上将该方法与人的掩蔽特性相结合。通过语音增强方法性能客观评测表明，该语音增强方法更好地抑制了噪声，有效地减小语音失真。
|
| 关 键 词： | 语音增强 听觉掩蔽阈值 最小均方误差（MMSE） |
| 收稿时间： | 2008-8-27 |
| 修稿时间： | 2008-11-11
|
Speech enhancement based on Laplacian model and masking |
| |
| XU Cui-xiang,MA Jian-fen.Speech enhancement based on Laplacian model and masking[J].Computer Engineering and Applications,2010,46(7):153-154. |
| |
| Authors: | XU Cui-xiang MA Jian-fen |
| |
| Affiliation: | XU Cui-xiang,MA Jian-fen College of Computer , Software,Taiyuan University of Technology,Taiyuan 030024,China |
| |
| Abstract: | An effective approach for attenuating acoustic noise and mitigating speech distortion is proposed.First,MMSE method is analysed when the clean speech is modeled by a Laplacian distribution and the noise is modeled by a Gaussian distribution.Then,human perceptual auditory masking threshold is incorporated into this approach when the threshold of spectral amplitude of enhanced speech is computed.The experiment result evaluated by objective measure shows the proposed method can achieve a more significant noise... |
| |
| Keywords: | speech enhancement masking properties Minimum Mean-Square Error(MMSE) |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载全文 |
|
