Verena Haunschmid, Ethan Manilov,
"audioLIME: Listenable Explanations Using Source Separation"
: Proceedings of the 13th International Workshop on Machine Learning and Music, European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2020, 2020
Original Titel:
audioLIME: Listenable Explanations Using Source Separation
Sprache des Titels:
Englisch
Original Buchtitel:
Proceedings of the 13th International Workshop on Machine Learning and Music, European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2020
Original Kurzfassung:
Deep neural networks (DNNs) are successfully applied in a
wide variety of music information retrieval (MIR) tasks but their predictions are usually not interpretable. We propose audioLIME, a method
based on Local Interpretable Model-agnostic Explanations (LIME), extended by a musical definition of locality. The perturbations used in
LIME are created by switching on/off components extracted by source
separation which makes our explanations listenable. We validate audioLIME on two different music tagging systems and show that it produces
sensible explanations in situations where a competing method cannot.
Forschungs-