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

Published: 31 Oct 2022, Last Modified: 04 Jan 2023NeurIPS 2022 AcceptReaders: Everyone
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.
Supplementary Material: pdf
13 Replies