Automatic musical pattern feature extraction using convolutional neural network

Music genre classification has been a challenging yet promising task in the field of music information retrieval (MIR). Due to the highly elusive characteristics of audio musical data, retrieving informative and reliable features from audio signals is crucial to the performance of any music genre classification system. Previous work on audio music genre classification systems mainly concentrated on using timbral features, which limits the performance. To address this problem, we propose a novel approach to extract musical pattern features in audio music using convolutional neural network (CNN), a model widely adopted in image information retrieval tasks. Our experiments show that CNN has strong capacity to capture informative features from the variations of musical patterns with minimal prior knowledge provided.