# Hyperbolic Distance-Based Speech Separation

arXiv: https://arxiv.org/abs/2401.03567 · HTML: https://mlsanity.com/paper/2401.03567/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jan 2024.

## Built on by (most cited first, 4 of 4)

- [A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four Stems](https://mlsanity.com/paper/2406.18747/) (2024)
- [Hyperbolic Additive Margin Softmax with Hierarchical Information for Speaker Verification](https://mlsanity.com/paper/2601.19709/) (2026)
- [Single-Channel Distance-Based Source Separation for Mobile GPU in Outdoor and Indoor Environments](https://mlsanity.com/paper/2501.03045/) (2025)
- [More Than A Shortcut: A Hyperbolic Approach To Early-Exit Networks](https://mlsanity.com/paper/2511.00641/) (2025)

## Abstract (arXiv)

In this work, we explore the task of hierarchical distance-based speech separation defined on a hyperbolic manifold. Based on the recent advent of audio-related tasks performed in non-Euclidean spaces, we propose to make use of the Poincar'e ball to effectively unveil the inherent hierarchical structure found in complex speaker mixtures. We design two sets of experiments in which the distance-based parent sound classes, namely "near" and "far", can contain up to two or three speakers (i.e., children) each. We show that our hyperbolic approach is suitable for unveiling hierarchical structure from the problem definition, resulting in improved child-level separation. We further show that a clear correlation emerges between the notion of hyperbolic certainty (i.e., the distance to the ball's origin) and acoustic semantics such as speaker density, inter-source location, and microphone-to-speaker distance.