We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Automatic Music Genre Classification Based on CRNN.
- Authors
Yu-Huei Cheng; Pang-Ching Chang; Duc-Man Nguyen; Che-Nan Kuo
- Abstract
In recent years, machine learning and deep learning technologies are maturing. The Convolutional Neural Networks (CNNs) are applied to all kinds of fields and various CNN-based fusion and combination methods are also appeared one after another. Due to the streaming media rapid growth, therefore the music genre classification is significant in the multimedia world. In order to raise the user’s efficiency when searching for different styles of music, we applied CNN combined with Recurrent Neural Network (RNN) architecture to implement a music genre classification model. In the pre-training step, the Mel-Frequency Cepstrum (MFC) is used as feature vector of sound samples. We use Librosa to convert original audio files into their MFC to achieve a sensory pattern close to that of humans hear. In this study, a model is trained by Mel-Frequency Cepstral Coefficients (MFCC) and CRNN method with the accuracy achieve to 43%. This model will continue to be improved in the future to identify the music style by extracting more sound features.
- Subjects
POPULAR music genres; DEEP learning; RECURRENT neural networks; CONVOLUTIONAL neural networks; MACHINE learning; STREAMING technology
- Publication
Engineering Letters, 2020, Vol 29, Issue 1, p312
- ISSN
1816-093X
- Publication type
Article