Mixture of Dynamical Variational Autoencoders for Multi-Source Trajectory Modeling and Separation

Published: 16 Dec 2023, Last Modified: 16 Dec 2023Accepted by TMLREveryoneRevisionsBibTeX
Abstract: In this paper, we propose a latent-variable generative model called mixture of dynamical variational autoencoders (MixDVAE) to model the dynamics of a system composed of multiple moving sources. A DVAE model is pre-trained on a single-source dataset to capture the source dynamics. Then, multiple instances of the pre-trained DVAE model are integrated into a multi-source mixture model with a discrete observation-to-source assignment latent variable. The posterior distributions of both the discrete observation-to-source assignment variable and the continuous DVAE variables representing the sources content/position are estimated using the variational expectation-maximization algorithm, leading to multi-source trajectories estimation. We illustrate the versatility of the proposed MixDVAE model on two tasks: a computer vision task, namely multi-object tracking, and an audio processing task, namely single-channel audio source separation. Experimental results show that the proposed method works well on these two tasks, and outperforms several baseline methods.
Submission Length: Long submission (more than 12 pages of main content)
Changes Since Last Submission: This is the camera ready version of the paper.
Code: https://github.com/linxiaoyu1/MixDVAE
Supplementary Material: zip
Assigned Action Editor: ~Pablo_Sprechmann1
License: Creative Commons Attribution 4.0 International (CC BY 4.0)
Submission Number: 1135