LMAC-TD: Producing Time Domain Explanations for Audio Classifiers
Abstract
Neural networks are typically black-boxes that remain opaque with regards to their decision mechanisms. Several works in the literature have proposed post-hoc explanation methods to alleviate this issue. This paper proposes LMAC-TD, a post-hoc explanation method that trains a decoder to produce explanations directly in the time domain. This methodology builds upon the foundation of L-MAC, Listenable Maps for Audio Classifiers, a method that produces faithful and listenable explanations. We incorporate SepFormer, a popular transformer-based time-domain source separation architecture. We show through a user study that LMAC-TD significantly improves the audio quality of the produced explanations while not sacrificing from faithfulness.
Keywords
Cite
@article{arxiv.2409.08655,
title = {LMAC-TD: Producing Time Domain Explanations for Audio Classifiers},
author = {Eleonora Mancini and Francesco Paissan and Mirco Ravanelli and Cem Subakan},
journal= {arXiv preprint arXiv:2409.08655},
year = {2024}
}
Comments
The first two authors contributed equally to this research. Author order is alphabetical