基于加权 Lehmer 均值的方向性稀疏滤波用于非均衡语音混合的盲分离
音频与语音处理
2021-07-21 v3 机器学习
声音
信号处理
摘要
在语音信号的盲源分离中,源频谱固有的不均衡性对依赖单源主导来估计混合矩阵的方法构成了挑战。我们提出一种基于方向性稀疏滤波(DSF)框架的算法,其利用带可学习权重的 Lehmer 均值来自适应地考虑源不均衡。在多个真实声学环境中的性能评估显示,与基线方法相比源分离有所改善。
引用
@article{arxiv.2102.00196,
title = {Directional Sparse Filtering using Weighted Lehmer Mean for Blind Separation of Unbalanced Speech Mixtures},
author = {Karn Watcharasupat and Anh H. T. Nguyen and Ching-Hui Ooi and Andy W. H. Khong},
journal= {arXiv preprint arXiv:2102.00196},
year = {2021}
}
备注
(c) 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works