LMAC-TD: Producing Time Domain Explanations for Audio Classifiers
Eleonora Mancini, Francesco Paissan, Mirco Ravanelli, Cem Subakan
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.
BibTeX
@inproceedings{icassp2025_lmactdproducingt,
title = {LMAC-TD: Producing Time Domain Explanations for Audio Classifiers},
author = {Eleonora Mancini and Francesco Paissan and Mirco Ravanelli and Cem Subakan},
booktitle = {ICASSP 2025},
year = {2025}
}