# Fast MVAE: Joint separation and classification of mixed sources based on multichannel variational autoencoder with auxiliary classifier

16 Dec 2018Li LiHirokazu KameokaShoji Makino

This paper proposes an alternative algorithm for multichannel variational autoencoder (MVAE), a recently proposed multichannel source separation approach. While MVAE is notable in its impressive source separation performance, the convergence-guaranteed optimization algorithm and that it allows us to estimate source-class labels simultaneously with source separation, there are still two major drawbacks, i.e., the high computational complexity and unsatisfactory source classification accuracy... (read more)

PDF Abstract