Holistic Approaches to Music Genre Classification using Efficient Transfer and Deep Learning Techniques

Optimizing the configuration of deep learning models for music genre classification

“…It should be mentioned that, in addition to the scenarios mentioned above, the effectiveness of the suggested approach has also been contrasted with the BAG technique offered by Prabhakar et al in Ref. [ 19 ] and the way of Yang et al in Ref. [ 15 ].…”

“…In Ref. [ 19 ], a study introduces five novel hybrid techniques for categorizing music genres. The classification methods used in this study are: the weighted visibility graph based elastic net sparse classifier (WVG-ELNSC), the sequential machine learning with stacked autoencoder (SDA), the Riemannian Alliance based tangent space-based mapping (RA-STM) with transfer learning technique, the Transfer SVM (TSVM), and a classifier combining Bidirectional Long Short Term Memory (BiLSTM) with Graphical Convolution Network (GCN), referred to as BAG.…”

Music Deep Learning: Deep Learning Methods for Music Signal Processing—A Review of the State-of-the-Art

“…The model achieves an accuracy of 89.71%. In [55], a complex architecture is used, combining a Bidirectional Long Short-Term Memory (BLSTM) model with an attention mechanism, paired with a Graphical Convolutional Network. Three datasets are tested, GTZAN [56], ISMIR [54] and MagnaTa-gATune [57].…”

“…Such approaches can harness the individual characteristics of each model to surpass their counterparts. Attention mechanism enhanced architectures is one such example [55], [94], [125], [161], [180], with more being developed [201]- [204]. Such approaches will surely lead the advances in the MDL field.…”

Three-Stage MPViT-DeepLab Transfer Learning for Community-Scale Green Infrastructure Extraction

“…When transfer learning is appropriately employed, the accuracy of deep learning tasks can be significantly improved while reducing training time. Transfer learning has found numerous applications in fields such as medicine [22,23], industry [24], finance [25,26], biology [27], music [28], environment [29], and computer vision [30,31].…”