English

LMAC-TD: Producing Time Domain Explanations for Audio Classifiers

Sound 2024-09-16 v1 Artificial Intelligence Machine Learning Audio and Speech Processing Signal Processing

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

R2 v1 2026-06-28T18:43:27.245Z