XANE Background Acoustic Embeddings: Ablation and Clustering Analysis
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.
Keywords
Cite
@article{arxiv.2407.06342,
title = {XANE Background Acoustic Embeddings: Ablation and Clustering Analysis},
author = {Dushyant Sharma and James Fosburgh and Sri Harsha Dumpala and Chandramouli Shama Sastri and Stanislav Yu. Kruchinin and Patrick A. Naylor},
journal= {arXiv preprint arXiv:2407.06342},
year = {2024}
}
Comments
arXiv admin note: substantial text overlap with arXiv:2406.05199