# Phone and speaker spatial organization in self-supervised speech representations

## TL;DR

This paper investigates how self-supervised speech representations encode phone and speaker information across different layers without relying on downstream models, revealing task-dependent encoding patterns.

## Contribution

It introduces methods to analyze spatial organization of speech attributes in representations without downstream models, highlighting task-dependent differences.

## Key findings

- Different layers encode formants and pitch variably.
- Representations cluster speech samples by phone and speaker.
- Encoding patterns depend on pretraining tasks.

## Abstract

Self-supervised representations of speech are currently being widely used for a large number of applications. Recently, some efforts have been made in trying to analyze the type of information present in each of these representations. Most such work uses downstream models to test whether the representations can be successfully used for a specific task. The downstream models, though, typically perform nonlinear operations on the representation extracting information that may not have been readily available in the original representation. In this work, we analyze the spatial organization of phone and speaker information in several state-of-the-art speech representations using methods that do not require a downstream model. We measure how different layers encode basic acoustic parameters such as formants and pitch using representation similarity analysis. Further, we study the extent to which each representation clusters the speech samples by phone or speaker classes using non-parametric statistical testing. Our results indicate that models represent these speech attributes differently depending on the target task used during pretraining.