Implementation of Convolutional Neural Network for Music Genre Classification
Faculty Mentor
Dr. Kim Jongyeop
Location
Poster 202
Session Format
Poster Presentation
Academic Unit
Department of Information Technology
Keywords
Allen E. Paulson College of Engineering and Computing Student Research Symposium, Mel Frequency Cepstral Coefficients, MFCCs, Hyper Parameter
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Presentation Type and Release Option
Presentation (File Not Available for Download)
Start Date
2022 12:00 AM
January 2022
COinS
Jan 1st, 12:00 AM
Implementation of Convolutional Neural Network for Music Genre Classification
Poster 202
- As the music industry grows rapidly and many songs are released, the importance of classifying music by genre is emerging. However, it is time-consuming for a person to judge a genre of music by directly listening to it.
- Recently, thanks to deep learning technology, research that can automatically classify using a model trained by machine learning without direct human involvement is being actively conducted.
- In this study, we focused on finding the Hyper parameter SET that improves the accuracy of the model by loading Json type music files from keras tensor flow and updating the logic to identify the genre of music with the CNN model.
