EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Hybrid Parallel Computing Architecture Based on CNN and Transformer for Music Genre Classification

Jiyang Chen, Xiaohong Ma, Shikuan Li, Sile Ma, Zhizheng Zhang, Xiaojing Ma

Electronics · 21.08.2024 · 13 (16) · 3313

DOI: 10.3390/electronics13163313 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 21.08.2024. Verfasst von Jiyang Chen und 5 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: special funds for central guiding local science and technology development: Industrialisation of internet of things terminal safety inspection platform, Jinan science and technology programme project: demonstration application of high performance big data security storage system, Shandong Provincial Natural Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Music genre classification (MGC) is the basis for the efficient organization, retrieval, and recommendation of music resources, so it has important research value. Convolutional neural networks (CNNs) have been widely used in MGC and achieved excellent results. However, CNNs cannot model global features well due to the influence of the local receptive field; these global features are crucial for classifying music signals with temporal properties. Transformers can capture long-range dependencies within an image thanks to adopting the self-attention mechanism. Nevertheless, there are still performance and computational cost gaps between Transformers and existing CNNs. In this paper, we propose a hybrid architecture (CNN-TE) based on CNN and Transformer encoder for MGC. Specifically, we convert the audio signals into mel spectrograms and feed them into a hybrid model for training. Our model employs a CNN to initially capture low-level and localized features from the spectrogram. Subsequently, these features are processed by a Transformer encoder, which models them globally to extract high-level and abstract semantic information. This refined information is then classified using a multi-layer perceptron. Our experiments demonstrate that this approach surpasses many existing CNN architectures when tested on the GTZAN and FMA datasets. Notably, it achieves these results with fewer parameters and a faster inference speed.

Förderung

  • special funds for central guiding local science and technology development: Industrialisation of internet of things terminal safety inspection platform
  • Jinan science and technology programme project: demonstration application of high performance big data security storage system
  • Shandong Provincial Natural Science Foundation

Zitieren

APA

Chen, J., Ma, X., Li, S., Ma, S., Zhang, Z., & Ma, X. (2024). A Hybrid Parallel Computing Architecture Based on CNN and Transformer for Music Genre Classification. Electronics, 13(16), 3313. https://doi.org/10.3390/electronics13163313

Vancouver

Chen J, Ma X, Li S, Ma S, Zhang Z, Ma X. A Hybrid Parallel Computing Architecture Based on CNN and Transformer for Music Genre Classification. Electronics. 2024;13(16):3313. doi:10.3390/electronics13163313

BibTeX
@article{Chen2024,
  author = {Chen, Jiyang and Ma, Xiaohong and Li, Shikuan and Ma, Sile and Zhang, Zhizheng and Ma, Xiaojing},
  title = {A Hybrid Parallel Computing Architecture Based on CNN and Transformer for Music Genre Classification},
  journal = {Electronics},
  year = {2024},
  volume = {13},
  number = {16},
  pages = {3313},
  doi = {10.3390/electronics13163313}
}
Kostenlos starten →