Feature Learning with Matrix Factorization Applied to Acoustic Scene Classification - Département Image, Données, Signal Accéder directement au contenu
Article Dans Une Revue IEEE/ACM Transactions on Audio, Speech and Language Processing Année : 2017

Feature Learning with Matrix Factorization Applied to Acoustic Scene Classification

Résumé

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.
Fichier principal
Vignette du fichier
bisot2017.pdf (631.05 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01362864 , version 1 (09-09-2016)
hal-01362864 , version 2 (24-08-2017)

Identifiants

Citer

Victor Bisot, Romain Serizel, Slim Essid, Gael Richard. Feature Learning with Matrix Factorization Applied to Acoustic Scene Classification. IEEE/ACM Transactions on Audio, Speech and Language Processing, 2017, 25 (6), pp.1216 - 1229. ⟨10.1109/TASLP.2017.2690570⟩. ⟨hal-01362864v2⟩
745 Consultations
1063 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More