Tackling Interpretability in Audio Classification Networks with Non-negative Matrix Factorization - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE/ACM Transactions on Audio, Speech and Language Processing Année : 2024

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

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.
Fichier principal
Vignette du fichier
L2I_TASLP-4.pdf (783.32 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04539879 , version 1 (09-04-2024)

Identifiants

Citer

Jayneel Parekh, Sanjeel Parekh, Pavlo Mozharovskyi, Gael Richard, Florence d'Alché-Buc. Tackling Interpretability in Audio Classification Networks with Non-negative Matrix Factorization. IEEE/ACM Transactions on Audio, Speech and Language Processing, 2024, 32, pp.1392--1405. ⟨10.1109/TASLP.2024.3358049⟩. ⟨hal-04539879⟩
5 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More