A Music Classification Model based on Metric Learning and Feature Extraction from MP3 Audio Files
This work addresses music similarity and classification for the entertainment industry, but it appears incremental as it builds on existing techniques like MFCC and PCA.
The paper tackled music classification by proposing a model that learns personalized metrics for customers using metric learning and feature extraction from MP3 files, with experiments showing promising results compared to baseline algorithms like K-means and SVM.
The development of models for learning music similarity and feature extraction from audio media files is an increasingly important task for the entertainment industry. This work proposes a novel music classification model based on metric learning and feature extraction from MP3 audio files. The metric learning process considers the learning of a set of parameterized distances employing a structured prediction approach from a set of MP3 audio files containing several music genres. The main objective of this work is to make possible learning a personalized metric for each customer. To extract the acoustic information we use the Mel-Frequency Cepstral Coefficient (MFCC) and make a dimensionality reduction with the use of Principal Components Analysis. We attest the model validity performing a set of experiments and comparing the training and testing results with baseline algorithms, such as K-means and Soft Margin Linear Support Vector Machine (SVM). Experiments show promising results and encourage the future development of an online version of the learning model.