Convolution Channel Separation And Frequency Sub-bands Aggregation For Music Genre Classification

Abstract

In music, short-term features such as pitch and tempo constitute long-term semantic features such as melody and narrative. A music genre classification (MGC) system should be able to analyze these features. In this research, we propose a novel framework that can extract and aggregate both short- and long-term features hierarchically. Our framework is based on ECAPA-TDNN, where all the layers that extract short-term features are affected by the layers that extract long-term features because of the back-propagation training. To prevent the distortion of short-term features, we devised the convolution channel separation technique that separates short-term features from long-term feature extraction paths. To extract more diverse features from our framework, we incorporated the frequency sub-bands aggregation method, which divides the input spectrogram along frequency bandwidths and processes each segment. We evaluated our framework using the Melon Playlist dataset which is a large-scale da

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyheo2022convolution

Related papers

• Music Genre Classification: A Comparative Analysis Of CNN And Xgboost Approaches With Mel-frequency Cepstral Coefficients And Mel Spectrograms (2024)0.00
• Music Genre Classification Using Spectral Analysis And Sparse Representation Of The Signals (2018)8.09
• A Novel Multimodal Music Genre Classifier Using Hierarchical Attention And Convolutional Neural Network (2020)0.00
• Deep Learning Based EDM Subgenre Classification Using Mel-spectrogram And Tempogram Features (2021)0.00
• Genre-agnostic Key Classification With Convolutional Neural Networks (2018)0.00
• Time-frequency Audio Features For Speech-music Classification (2018)0.00
• Multi-level And Multi-scale Feature Aggregation Using Pre-trained Convolutional Neural Networks For Music Auto-tagging (2017)15.43
• Ms-sincresnet: Joint Learning Of 1D And 2D Kernels Using Multi-scale Sincnet And Resnet For Music Genre Classification (2021)13.13