Nonlinear ISA with Auxiliary Variables for Learning Speech Representations

Amrith Setlur, Barnabás Póczos, Alan W. Black


This paper extends recent work on nonlinear Independent Component Analysis ( ica) by introducing a theoretical framework for nonlinear Independent Subspace Analysis ( isa) in the presence of auxiliary variables. Observed high dimensional acoustic features like log Mel spectrograms can be considered as surface level manifestations of nonlinear transformations over individual multivariate sources of information like speaker characteristics, phonological content etc. Under assumptions of energy based models we use the theory of nonlinear isa to propose an algorithm that learns unsupervised speech representations whose subspaces are independent and potentially highly correlated with the original non-stationary multivariate sources. We show how nonlinear ica with auxiliary variables can be extended to a generic identifiable model for subspaces as well while also providing sufficient conditions for the identifiability of these high dimensional subspaces. Our proposed methodology is generic and can be integrated with standard unsupervised approaches to learn speech representations with subspaces that can theoretically capture independent higher order speech signals. We evaluate the gains of our algorithm when integrated with the Autoregressive Predictive Coding ( apc) model by showing empirical results on the speaker verification and phoneme recognition tasks.


 DOI: 10.21437/Interspeech.2020-3050

Cite as: Setlur, A., Póczos, B., Black, A.W. (2020) Nonlinear ISA with Auxiliary Variables for Learning Speech Representations. Proc. Interspeech 2020, 180-184, DOI: 10.21437/Interspeech.2020-3050.


@inproceedings{Setlur2020,
  author={Amrith Setlur and Barnabás Póczos and Alan W. Black},
  title={{Nonlinear ISA with Auxiliary Variables for Learning Speech Representations}},
  year=2020,
  booktitle={Proc. Interspeech 2020},
  pages={180--184},
  doi={10.21437/Interspeech.2020-3050},
  url={http://dx.doi.org/10.21437/Interspeech.2020-3050}
}