Quantifying Dimensional Independence in Speech: An Information-Theoretic Framework for Disentangled Representation Learning
Abstract
Speech signals encode emotional, linguistic, and pathological information within a shared acoustic channel; however, disentanglement is typically assessed indirectly through downstream task performance. We introduce an information-theoretic framework to quantify cross-dimension statistical dependence in handcrafted acoustic features by integrating bounded neural mutual information (MI) estimation with non-parametric validation. Across six corpora, cross-dimension MI remains low, with tight estimation bounds ( nats), indicating weak statistical coupling in the data considered, whereas Source--Filter MI is substantially higher (0.47 nats). Attribution analysis, defined as the proportion of total MI attributable to source versus filter components, reveals source dominance for emotional dimensions (80\%) and filter dominance for linguistic and pathological dimensions (60\% and 58\%, respectively). These findings provide a principled framework for quantifying dimensional independence in speech.
Cite
@article{arxiv.2602.20592,
title = {Quantifying Dimensional Independence in Speech: An Information-Theoretic Framework for Disentangled Representation Learning},
author = {Bipasha Kashyap and Björn W. Schuller and Pubudu N. Pathirana},
journal= {arXiv preprint arXiv:2602.20592},
year = {2026}
}