Acoustic Denoising Using Dictionary Learning With Spectral and Temporal Regularization.

Colin Vaz,Vikram Ramanarayanan,Shrikanth Narayanan

IEEE/ACM Transactions on Audio, Speech, and Language Processing（2018）

引用 9|浏览32

暂无评分

摘要

We present a method for speech enhancement of data collected in extremely noisy environments, such as those obtained during magnetic resonance imaging scans. We propose an algorithm based on dictionary learning to perform this enhancement. We use complex nonnegative matrix factorization with intrasource additivity (CMF-WISA) to learn dictionaries of the noise and speech+noise portions of the data ...

查看译文

关键词

Speech,Magnetic resonance imaging,Noise reduction,Noise measurement,Algorithm design and analysis,Spatial resolution,Three-dimensional displays

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要