A Combination of Hand-Crafted and Hierarchical High-Level Learnt Feature Extraction for Music Genre Classification

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

[1]  Andreas Rauber,et al.  Evaluation of Feature Extractors and Psycho-Acoustic Transformations for Music Genre Classification , 2005, ISMIR.

[2]  Constantine Kotropoulos,et al.  Music Genre Classification Using Locality Preserving Non-Negative Tensor Factorization and Sparse Representations , 2009, ISMIR.

[3]  Tao Li,et al.  A comparative study on content-based music genre classification , 2003, SIGIR.

[4]  Yann LeCun,et al.  Unsupervised Learning of Sparse Features for Scalable Audio Classification , 2011, ISMIR.

[5]  Michael S. Lewicki,et al.  Efficient auditory coding , 2006, Nature.

[6]  Marc'Aurelio Ranzato,et al.  A Unified Energy-Based Framework for Unsupervised Learning , 2007, AISTATS.

[7]  Peter Knees,et al.  USING BLOCK-LEVEL FEATURES FOR GENRE CLASSIFICATION , TAG CLASSIFICATION AND MUSIC SIMILARITY ESTIMATION , 2010 .

[8]  Douglas Eck,et al.  Learning Features from Music Audio with Deep Belief Networks , 2010, ISMIR.

[9]  George Tzanetakis,et al.  Musical genre classification of audio signals , 2002, IEEE Trans. Speech Audio Process..

[10]  Douglas Eck,et al.  Scalable Genre and Tag Prediction with Spectral Covariance , 2010, ISMIR.

[11]  Antoni B. Chan,et al.  Genre Classification and the Invariance of MFCC Features to Key and Tempo , 2011, MMM.

[12]  Tao Li,et al.  Factors in automatic musical genre classification of audio signals , 2003, 2003 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (IEEE Cat. No.03TH8684).

[13]  Douglas Eck,et al.  Aggregate features and ADABOOST for music classification , 2006, Machine Learning.

[14]  Geoffrey E. Hinton,et al.  To recognize shapes, first learn to generate images. , 2007, Progress in brain research.

[15]  Peter Knees,et al.  Automatic Music Tag Classification Based On Block-Level Features , 2010 .

[16]  Luiz S. Oliveira,et al.  Music genre recognition using spectrograms , 2011, 2011 18th International Conference on Systems, Signals and Image Processing.

[17]  Jiao Licheng.  Research on Computation of GLCM of Image Texture , 2006 .

[18]  Jyh-Shing Roger Jang,et al.  Music Genre Classification via Compressive Sampling , 2010, ISMIR.

[19]  Constantine Kotropoulos,et al.  Music genre classification via Topology Preserving Non-Negative Tensor Factorization and sparse representations , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

[20]  Antoni B. Chan,et al.  Automatic Musical Pattern Feature Extraction Using Convolutional Neural Network , 2010 .