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

Jayneel Parekh, Sanjeel Parekh, Pavlo Mozharovskyi, Florence d'Alché-Buc, Gaël Richard

Keywords: audio interpretability, post-hoc explainability, non-negative matrix factorization, audio recognition

Abstract: 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.

Community Implementations: [ 6 code implementations](https://www.catalyzex.com/paper/listen-to-interpret-post-hoc-interpretability/code)