Feature Learning with Matrix Factorization Applied to Acoustic Scene Classification

Abstract : In this paper, we study the usefulness of various matrix factorization methods for learning features to be used for the specific Acoustic Scene Classification problem. A common way of addressing ASC has been to engineer features capable of capturing the specificities of acoustic environments. Instead, we show that better representations of the scenes can be automatically learned from time-frequency representations using matrix factorization techniques. We mainly focus on extensions including sparse, kernel-based, convolutive and a novel supervised dictionary learning variant of Principal Component Analysis and Nonnegative Matrix Factorization. An experimental evaluation is performed on two of the largest ASC datasets available in order to compare and discuss the usefulness of these methods for the task. We show that the unsupervised learning methods provide better representations of acoustic scenes than the best conventional hand-crafted features on both datasets. Furthermore, the introduction of a novel nonnegative supervised matrix factorization model and Deep Neural networks trained on spectrograms, allow us to reach further improvements.
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01362864
Contributor : Victor Bisot <>
Submitted on : Thursday, August 24, 2017 - 9:30:17 AM
Last modification on : Wednesday, April 3, 2019 - 1:22:55 AM

File

bisot2017.pdf
Files produced by the author(s)

Identifiers

Citation

Victor Bisot, Romain Serizel, Slim Essid, Gaël Richard. Feature Learning with Matrix Factorization Applied to Acoustic Scene Classification. IEEE/ACM Transactions on Audio, Speech and Language Processing, Institute of Electrical and Electronics Engineers, 2017, 25 (6), pp.1216 - 1229. ⟨10.1109/TASLP.2017.2690570⟩. ⟨hal-01362864v2⟩

Share

Metrics

Record views

582

Files downloads

437