摘要
单通道子空间语音增强算法在加性噪声为白噪声的情况下,效果比较理想。加性噪声为有色噪声的情况下,通常用广义奇异值分解算法来进行处理。为了降低低信噪比情况下残留的音乐噪声,结合人耳的听觉掩蔽效应,提出了一种基于感官抑制的广义奇异值分解算法。实验结果显示,该算法能够明显地提高语音质量、可懂度和识别率,特别是在加性噪声是有色噪声的情况下实验结果明显优于其他的语音增强算法。
Generalized singular value decomposition is very useful when the additive noise is white. But the residual musical noise is still perceivable under lower signal-to-noise conditions. Therefore, a perceptually constrained Generalized Singular Value Decomposition （GSVD）, which is refered to PCGSVD algorithm, is furtherly proposed to incoporate the masking properties of human auditory system to make sure the residual noise to be under the Auditory Masking Threshold （AMT）.
出处
《计算机应用》
CSCD
北大核心
2009年第B06期337-339,344,共4页
journal of Computer Applications
基金
广西自然科学基金资助项目(0639028)
关键词
听觉掩蔽门限
广义奇异值分解
信号子空间
语音增强
Auditory Masking Threshold （AMT）
generalized singular value decomposition
signal subspace
speech enhancement
