A hybrid neural network model based on optimized margin softmax loss function for music classification

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

View graph of relations

Author(s)

  • Jingxian Li
  • Lixin Han
  • Xin Wang
  • Yang Wang
  • Jianhua Xia
  • Yi Yang
  • Bing Hu
  • Shu Li

Related Research Unit(s)

Detail(s)

Original languageEnglish
Journal / PublicationMultimedia Tools and Applications
Online published16 Oct 2023
Publication statusOnline published - 16 Oct 2023

Abstract

Music classification has achieved great progress due to the development of Convolutional Neural Networks (CNNs), which is important for music retrieval and recommendation. However, CNN cannot capture temporal information from music audio, which restricts the prediction performance of the model. To address the issue, we propose a Convolutional Neural Network-Long Short Term Memory (CNN-LSTM) model to learn local spatial features by CNN and learn temporal dependencies by LSTM. In addition, the traditional softmax loss function commonly lacks sufficient discrimination in music classification. Therefore, we propose an additive angular margin and cosine margin softmax (AACM-Softmax) loss function to improve classification results, which minimizes intra-class variances and maximizes inter-class variances simultaneously by enforcing combined margin penalties. Furthermore, we combine the CNN-LSTM model with AACM-Softmax loss function to comprehensively improve the classification performance by learning temporal-dependencies-included discriminative essential features. Extensive experiments on music genre datasets and music emotion datasets show that the proposed model consistently outperforms other models. © 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

Research Area(s)

  • AACM-Softmax, CNN-LSTM model, Combined margin penalties, Music classification, Temporal dependencies

Citation Format(s)

A hybrid neural network model based on optimized margin softmax loss function for music classification. / Li, Jingxian; Han, Lixin; Wang, Xin et al.
In: Multimedia Tools and Applications, 16.10.2023.

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review