Feature projection-based unsupervised domain adaptation for acoustic scene classification

Mezza AI, Habets E, Müller M, Sarti A (2020)

Publication Type: Conference contribution

Publication year: 2020

Publisher: IEEE Computer Society

Book Volume: 2020-September

Conference Proceedings Title: IEEE International Workshop on Machine Learning for Signal Processing, MLSP

ISBN: 9781728166629

DOI: 10.1109/MLSP49062.2020.9231836

Abstract

The mismatch between the data distributions of training and test data acquired under different recording conditions and using different devices is known to severely impair the performance of acoustic scene classification (ASC) systems. To address this issue, we propose an unsupervised domain adaptation method for ASC based on the projection of spectrooral features extracted from both the source and target domain onto the principal subspace spanned by the eigenvectors of the sample covariance matrix of source-domain training data. Using the TUT Urban Acoustic Scenes 2018 Mobile Development dataset we show that the proposed method outperforms state-of-the-art unsupervised domain adaptation techniques when applied jointly with a convolutional ASC model and can also be practically employed as a feature extraction procedure for shallower artificial neural networks.

Authors with CRIS profile

Emanuël Habets Professur für wahrnehmungsbasierte räumliche Audiosignalverarbeitung (AudioLabs) (Stiftungsprofessur) Meinard Müller International Audio Laboratories Erlangen (AudioLabs)

Involved external institutions

Politecnico di Milano IT Italy (IT)

How to cite

APA:

Mezza, A.I., Habets, E., Müller, M., & Sarti, A. (2020). Feature projection-based unsupervised domain adaptation for acoustic scene classification. In IEEE International Workshop on Machine Learning for Signal Processing, MLSP. IEEE Computer Society.

MLA:

Mezza, Alessandro Ilic, et al. "Feature projection-based unsupervised domain adaptation for acoustic scene classification." Proceedings of the 30th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2020 IEEE Computer Society, 2020.

BibTeX: Download