Listen to Interpret: Post-hoc Interpretability for Audio Networks with NMF - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Listen to Interpret: Post-hoc Interpretability for Audio Networks with NMF

Résumé

This paper tackles post-hoc interpretability for audio processing networks. Our goal is to interpret decisions of a trained network in terms of high-level audio objects that are also listenable for the end-user. To this end, we propose a novel interpreter design that incorporates non-negative matrix factorization (NMF). In particular, a regularized interpreter module is trained to take hidden layer representations of the targeted network as input and produce time activations of pre-learnt NMF components as intermediate outputs. 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 popular benchmarks, including a real-world multi-label classification task.
Fichier principal
Vignette du fichier
NeurIPS-2022-listen-to-interpret-post-hoc-interpretability-for-audio-networks-with-nmf-Paper-Conference.pdf (484.2 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04168435 , version 1 (21-07-2023)

Identifiants

  • HAL Id : hal-04168435 , version 1

Citer

Parekh Jayneel, Parekh Sanjeel, Mozharovskyi Pavlo, d'Alché-Buc Florence, Gael Richard. Listen to Interpret: Post-hoc Interpretability for Audio Networks with NMF. Advances in Neural Information Processing Systems, 2022, New Orleans, United States. ⟨hal-04168435⟩
12 Consultations
15 Téléchargements

Partager

Gmail Facebook X LinkedIn More