Tackling Interpretability in Audio Classification Networks With Non-negative Matrix Factorization-Reference-Cited by-同舟云学术

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

Published:2024 Issue: Volume:32 Page:1392-1405
ISSN:2329-9290
Container-title:IEEE/ACM Transactions on Audio, Speech, and Language Processing
language:
Short-container-title:IEEE/ACM Trans. Audio Speech Lang. Process.

Author:

Parekh Jayneel¹^ORCID,Parekh Sanjeel¹^ORCID,Mozharovskyi Pavlo¹^ORCID,Richard Gaël¹^ORCID,d'Alché-Buc Florence¹^ORCID

Affiliation:

1. Laboratoire de Traitement et Communication de l'Information (LTCI), Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Link

http://xplorestaging.ieee.org/ielx7/6570655/10304349/10413597.pdf?arnumber=10413597

Reference66 articles.

1. The (Un)reliability of Saliency Methods

2. On the robustness of interpretability methods;Alvarez-Melis,2018

3. You shouldnt trust me: Learning models which conceal unfairness from multiple explanation methods;Dimanov,2020

4. All models are wrong, but many are useful: Learning a variables importance by studying an entire class of prediction models simultaneously;Fisher;J. Mach. Learn. Res.,2019

5. Interpretable machine learning: Fundamental principles and 10 grand challenges

Cited by 3 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. A Multi-Task Network: Improving Unmanned Underwater Vehicle Self-Noise Separation via Sound Event Recognition;Journal of Marine Science and Engineering;2024-09-05

2. Focal Modulation Networks for Interpretable Sound Classification;2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW);2024-04-14

3. An Explainable Proxy Model for Multilabel Audio Segmentation;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14