稀疏低秩模型下的单通道自学习语音增强算法

针对现有基于字典学习的增强算法依赖先验信息的问题，基于矩阵的稀疏低秩分解提出一种无监督的单通道语音增强算法。该算法首先通过稀疏低秩分解将带噪语音的幅度谱分解为低秩、稀疏和噪声三部分，然后通过对低秩部分进行自学习构建出噪声字典，最后利用所得噪声字典和乘性迭代准则于低秩和稀疏部分中分离出纯净语音。相较于其他基于字典学习的语音增强算法，本文所提算法无需语音或噪声的先验信息，因而更加方便和实用。实验结果显示，本文算法能够在保留语音谐波结构的同时有效抑制噪声，增强效果明显优于鲁棒主成分分析和多带谱减法。

A Self-Learning Approach for Monaural Speech Enhancement Based on Sparse and Low-Rank Matrix Decomposition

To resolve the prior dependency of existing enhancement algorithms based on dictionary learning, an unsupervised self-learning approach for speech enhancement in one channel record is presented. Firstly, the algorithm decomposes the magnitude spectrum of noisy speech efficiently into low-rank part, sparse part and noise part. Then, the dictionary of noise is acquired by learning the low-rank part. Finally, the clean speech is separated by using the acquired noise dictionary and multiplicative update rules. As the approach is unsupervised, it is more convenient and practice than other enhancement methods based on dictionary learning. The experiment results show that the approach proposed outperforms other enhancement methods like robust principal component analysis and multiband spectra subtraction in terms of harmonic structure maintaining and noise suppression.