A Combination of Hand-crafted and Hierarchical High-level Learnt Feature Extraction for Music Genre Classification

Julien Martel (1) , Toru Nakashika , Christophe Garcia (2) , Khalid Idrissi (2)

1 LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
2 imagine - Extraction de Caractéristiques et Identification

In this paper, we propose a new approach for automatic musical genre classification which relies on learning a feature hierarchy with a deep learning architecture over hand-crafted feature extracted from the audio signal. Unlike the state-of-the-art approaches, our scheme applies an unsupervised learning algorithm based on Deep Belief Networks (DBN) on block-wise MFCC (that we treat as 2D images) followed by a supervised learning algorithm for fine-tuning using the labels for the music. Experiments performed on the GTZAN dataset show that the proposed scheme clearly outperforms the state-of-the-art approaches.

Domaines: Informatique [cs]

Julien Martel, Toru Nakashika, Christophe Garcia, Khalid Idrissi. A Combination of Hand-crafted and Hierarchical High-level Learnt Feature Extraction for Music Genre Classification. International Conference on Artificial Neural Networks (ICANN 2013), Sep 2013, Sofia, Bulgaria. pp.397-404, ⟨10.1007/978-3-642-40728-4_50⟩. ⟨hal-01339196⟩