FastGMVAE: Underdetermined Source Separation Based on Multichannel Variational Auto-Encoder

2021 4th International Conference on Information Communication and Signal Processing (ICICSP)（2021）

引用 0|浏览1

暂无评分

摘要

In this paper, Fast Generalized Multichannel Variational Auto-Encoder (FastGMVAE) is proposed by combining advantages of multichannel nonnegative matrix factorization and multichannel variational autoencoder to address underdetermined multichannel blind source separation problems. The proposed algorithm uses conditional variational autoencoder instead of the nonnegative matrix factorization model ...

查看译文

关键词

Simulation,Computational modeling,Signal processing algorithms,Blind source separation,Computational efficiency,Covariance matrices,Task analysis

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