Exploring Data Augmentation to Improve Music Genre Classification with ConvNets

In this work we address the automatic music genre classification as a pattern recognition task. The content of the music pieces were handled in the visual domain, using spectrograms created from the audio signal. This kind of image has been successfully used in this task since 2011 by extracting handcrafted features based on texture, since it is the main visual attribute found in spectrograms. In this work, the patterns were described by representation learning obtained with the use of convolutional neural network (CNN). CNN is a deep learning architecture and it has been widely used in the pattern recognition literature. Overfitting is a recurrent problem when a classification task is addressed by using CNN, it may occur due to the lack of training samples and/or due to the high dimensionality of the space. To increase the generalization capability we propose to explore data augmentation techniques. In this work, we have carefully selected strategies of data augmentation that are suitable for this kind of application, which are: adding noise, pitch shifting, loudness variation and time stretching. Experiments were conducted on the Latin Music Database (LMD), and the best obtained accuracy overcame the state of the art considering approaches based only in CNN.

[1]  Yann LeCun,et al.  Moving Beyond Feature Design: Deep Architectures and Automatic Feature Learning in Music Informatics , 2012, ISMIR.

[2]  Lawrence D. Jackel,et al.  Handwritten Digit Recognition with a Back-Propagation Network , 1989, NIPS.

[3]  Jiri Matas,et al.  On Combining Classifiers , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Luiz Eduardo Soares de Oliveira,et al.  Music genre classification using LBP textural features , 2012, Signal Process..

[5]  Alessandro L. Koerich,et al.  The Latin Music Database , 2008, ISMIR.

[6]  Juan Pablo Bello,et al.  Rethinking Automatic Chord Recognition with Convolutional Neural Networks , 2012, 2012 11th International Conference on Machine Learning and Applications.

[7]  Jean-Jacques E. Slotine,et al.  Audio classification from time-frequency texture , 2008, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[8]  Alessandro Lameiras Koerich,et al.  Music genre recognition based on visual features with dynamic ensemble of classifiers selection , 2013, 2013 20th International Conference on Systems, Signals and Image Processing (IWSSIP).

[9]  Andreas F. Ehmann,et al.  Lyric Text Mining in Music Mood Classification , 2009, ISMIR.

[10]  Jan Schlüter,et al.  Musical Onset Detection with Convolutional Neural Networks , 2013 .

[11]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

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

[13]  Lior Shamir,et al.  Computer analysis of similarities between albums in popular music , 2014, Pattern Recognit. Lett..

[14]  Benjamin Schrauwen,et al.  Deep content-based music recommendation , 2013, NIPS.

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

[16]  Luiz Eduardo Soares de Oliveira,et al.  An evaluation of Convolutional Neural Networks for music classification using spectrograms , 2017, Appl. Soft Comput..

[17]  Tetsuya Takiguchi,et al.  Local-feature-map Integration Using Convolutional Neural Networks for Music Genre Classification , 2012, INTERSPEECH.

[18]  Vincent Lostanlen,et al.  Deep Convolutional Networks on the Pitch Spiral For Music Instrument Recognition , 2016, ISMIR.

[19]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

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

[21]  Grzegorz Gwardys,et al.  Deep Image Features in Music Information Retrieval , 2014 .

[22]  Thomas Grill,et al.  Exploring Data Augmentation for Improved Singing Voice Detection with Neural Networks , 2015, ISMIR.

[23]  Thomas Hofmann,et al.  Audio Based Bird Species Identification using Deep Learning Techniques , 2016, CLEF.

[24]  Arthur Flexer,et al.  A Closer Look on Artist Filters for Musical Genre Classification , 2007, ISMIR.

[25]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

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

[27]  François Pachet,et al.  Representing Musical Genre: A State of the Art , 2003 .

[28]  Loris Nanni,et al.  Combining visual and acoustic features for music genre classification , 2016, Expert Syst. Appl..

[29]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[30]  Luc Van Gool,et al.  Deep Convolutional Neural Networks and Data Augmentation for Acoustic Event Detection , 2016, ArXiv.

[31]  Jens Grivolla,et al.  Multimodal Music Mood Classification Using Audio and Lyrics , 2008, 2008 Seventh International Conference on Machine Learning and Applications.

[32]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.