XANE Background Acoustic Embeddings: Ablation and Clustering Analysis

TL;DR

This paper analyzes the XANE acoustic embeddings system, demonstrating how joint parameter estimation improves explainability and showing that these embeddings outperform other methods in clustering tasks with high F1 scores.

Contribution

The paper provides an ablation and clustering analysis of XANE, highlighting the benefits of joint acoustic parameter estimation and its superior performance in clustering tasks.

Findings

Joint acoustic parameter estimation improves XANE performance.

XANE embeddings achieve a 92% mean F1 score in clustering tasks.

XANE embeddings outperform WavLM-based embeddings and complement speaker embeddings.

Abstract

We explore the recently proposed explainable acoustic neural embedding~(XANE) system that models the background acoustics of a speech signal in a non-intrusive manner. The XANE embeddings are used to estimate specific parameters related to the background acoustic properties of the signal which allows the embeddings to be explainable in terms of those parameters. We perform ablation studies on the XANE system and show that estimating all acoustic parameters jointly has an overall positive effect. Furthermore, we illustrate the value of XANE embeddings by performing clustering experiments on unseen test data and show that the proposed embeddings achieve a mean F1 score of 92\% for three different tasks, outperforming significantly the WavLM based signal embeddings and are complimentary to speaker embeddings.