Project DetailsIn this work, we created a model based on deep neural networks to classify music genres. During the process, we segmented each song into song excerpts and fed them into the model for training, validation, and testing. Throughout the project, we utilized the classification of songs with a single genre from the MTG-Jamendo song database, which involved working with a database of songs divided into genres in an unbalanced manner (the number of songs from each genre varies significantly). Therefore, we chose to work only with the ten largest genres and used different weighting schemes in hopes of improving the results.
Additionally, we employed the "majority rules" principle to ensure that all parts of the song fall under the same category (training/validation/testing) in the model. Then, we aggregated the results from the model's output for each song, thus creating a histogram of genre classification for each song, where the genre with the highest number of occurrences determines the final classification.
