Towards Robust Unsupervised Disentanglement of Sequential Data – A Case Study Using Music Audio


Disentangled sequential autoencoders (DSAEs) represent a class of probabilistic graphical models that describes an observed sequence with dynamic latent variables and a static latent variable. The former encode information at a frame rate identical to the observation, while the latter globally governs the entire sequence. This introduces an inductive bias and facilitates unsupervised disentanglement of the underlying local and global factors. In this paper, we show that the vanilla DSAE suffers from being sensitive to the choice of model architecture and capacity of the dynamic latent variables, and is prone to collapse the static latent variable. As a countermeasure, we propose TS-DSAE, a two-stage training framework that frst learns sequence-level prior distributions, which are subsequently employed to regularise the model and facilitate auxiliary objectives to promote disentanglement. The proposed framework is fully unsupervised and robust against the global factor collapse problem across a wide range of model confgurations. It also avoids typical solutions such as adversarial training which usually involves laborious parameter tuning, and domainspecifc data augmentation. We conduct quantitative and qualitative evaluations to demonstrate its robustness in terms of disentanglement on both artifcial and real-world music audio datasets.


June 2023 | ICASSP

Contrastive Learning-based Audio to Lyrics Alignment for Multiple Languages

Simon Durand, Daniel Stoller, Sebastian Ewert

March 2023 | CLeaR - Causal Learning and Reasoning

Non-parametric identifiability and sensitivity analysis of synthetic control models

Jakob Zeitler, Athanasios Vlontzos, Ciarán Mark Gilligan-Lee

March 2023 | CLeaR - Causal Learning and Reasoning

Estimating long-term causal effects from short-term experiments and long-term observational data with unobserved confounding

Graham Van Goffrier, Lucas Maystre, Ciarán Mark Gilligan-Lee