| 基于数据驱动字典和稀疏表示的语音增强 |
| |
| 引用本文： | 孙林慧,杨震.基于数据驱动字典和稀疏表示的语音增强[J].信号处理,2011,27(12). |
| |
| 作者姓名： | 孙林慧 杨震 |
| |
| 作者单位： | 南京邮电大学通信与信息工程学院;“宽带无线通信与传感网技术”教育部重点实验室,江苏南京210003 |
| |
| 基金项目： | 国家重大基础研究973课题(2011CB302903); 国家自然科学基金项目(60971129); 江苏省普通高校研究生科研创新计划项目(CX10B_191Z,CX10B_189Z) |
| |
| 摘 要： | 本文提出了一种基于数据驱动字典和过完备稀疏表示的自适应语音增强方法.首先在训练阶段采用干净语音基于K奇异值分解(K-singular value decomposition,K-SVD)算法训练过完备字典,然后在测试阶段根据含噪语音的噪声方差自适应选择最优的阈值,采用正交匹配追踪算法对含噪语音信号在过完备字典上进行稀疏分解,最后利用系数稀疏表示重构语音信号,从而达到语音增强的目.该方法不像传统语音增强方法那样减少或消去噪声,而是从字典中选取适当的原子表示纯净信号,从而把纯净信号从含噪信号中分离出来.对白噪声和有色噪声环境下重构语音进行了主客观评价.仿真结果显示:该方法能有效去除加性噪声,并且改善了语音质量.
|
| 关 键 词： | 语音增强 稀疏表示 过完备字典 正交匹配追踪 奇异值分解算法 |
Speech Enhancement Based on Data-Driven Dictionary and Sparse Representation |
| |
| SUN Lin-hui
,
YANG Zhen.Speech Enhancement Based on Data-Driven Dictionary and Sparse Representation[J].Signal Processing,2011,27(12). |
| |
| Authors: | SUN Lin-hui YANG Zhen |
| |
| Affiliation: | SUN Lin-hui YANG Zhen (College of Communication and Information Engineering,Key Lab of Broadband Wireless Communication and Sensor Network Technology Ministry of Education,Nanjing University of Posts and Telecommunications,Nanjing,Jiangsu 210003,China) |
| |
| Abstract: | An adaptive speech enhancement method based on Data-Driven Dictionary and overcompletely sparse representation theory is proposed.Firstly,using the K-singular value decomposition(K-SVD) algorithm,a dictionary that describes the clean speech content effectively is trained.Secondly,the prime threshold is adaptively selected according to noise variance of original noisy speech signal and the speech signal's sparsest coefficient vector is obtained through Orthogonal Matching Pursuit algorithm.And then the speec... |
| |
| Keywords: | speech enhancement sparse representation overcomplete dictionary Orthogonal Matching Pursuit singular value decomposition algorithm |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
