• Albert Jimenez

Music Genre Recognition

Our objective in this project was training a deep learning model to be able to recognize a song music genre. We used the GTZAN dataset to test our approach.

We adapt the model from Choi et al. to train a custom music genre classification system with our own genres and data. The model takes as an input the spectogram of music frames and analyzes the image using a Convolutional Neural Network (CNN) plus a Recurrent Neural Network (RNN). We compute the genre every 30 seconds of music and provide the average genre in the end. The output of the system is a vector of predicted genres for the song.

We fine-tune Choi's model with a small dataset (30 songs per genre) and test it on the GTZAN dataset achieving a final accuracy of 80%.

Instructions to run the code and the model can be found in GitHub. There are also Slides and the Report describing all the results.


Predicted genres per song section

Average genre predictions

  • github
  • White LinkedIn Icon
  • White Twitter Icon
  • White Instagram Icon