Passer à la navigation principale Passer à la recherche Passer au contenu principal

Tackling Interpretability in Audio Classification Networks With Non-negative Matrix Factorization

  • Institut Polytechnique de Paris

Résultats de recherche: Contribution à un journal › Article › Revue par des pairs

13 Citations (Scopus)

Résumé

This article tackles two major problem settings for interpretability of audio processing networks, post-hoc and by-design interpretation. For post-hoc interpretation, we aim to interpret decisions of a network in terms of high-level audio objects that are also listenable for the end-user. This is extended to present an inherently interpretable model with high performance. To this end, we propose a novel interpreter design that incorporates non-negative matrix factorization (NMF). In particular, an interpreter is trained to generate a regularized intermediate embedding from hidden layers of a target network, learnt as time-activations of a pre-learnt NMF dictionary. Our methodology allows us to generate intuitive audio-based interpretations that explicitly enhance parts of the input signal most relevant for a network's decision. We demonstrate our method's applicability on a variety of classification tasks, including multi-label data for real-world audio and music.

langue originaleAnglais
Pages (de - à)1392-1405
Nombre de pages14
journalIEEE/ACM Transactions on Audio Speech and Language Processing
Volume32
Les DOIs
étatPublié - 1 janv. 2024

Empreinte digitale

Examiner les sujets de recherche de « Tackling Interpretability in Audio Classification Networks With Non-negative Matrix Factorization ». Ensemble, ils forment une empreinte digitale unique.

Contient cette citation