EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Research on Urban Sound Classification based on ConvNeXt-FECA Model

Tianxiang Zhu

Frontiers in Computing and Intelligent Systems · 30.09.2025 · 13 (3) · 39-45

DOI: 10.54097/bha9rp62 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Computing and Intelligent Systems, online erschienen am 30.09.2025. Verfasst von Tianxiang Zhu. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the increasing severity of urban sound pollution, efficient and accurate urban sound classification and recognition has become an important topic in the field of urban environmental monitoring. In this paper, we propose an urban noise classification method based on the Frequency Enhanced Convolution Attention (ConvNeXt-FECA) model. By fusing the Spectrogram and MFCC features in the early stage, the method makes full use of the advantages of the two features, and introduces the Frequency Enhanced Convolutional Attention Mechanism (FECA) to adaptively pay attention to the changes in the frequency band of the audio signal, which effectively improves the classification performance. Experimental results show that the classification accuracy of the ConvNeXt-FECA model is 98.5% on the Urban Sound8K dataset, showing strong robustness and generalization ability.

Zitieren

APA

Zhu, T. (2025). Research on Urban Sound Classification based on ConvNeXt-FECA Model. Frontiers in Computing and Intelligent Systems, 13(3), 39-45. https://doi.org/10.54097/bha9rp62

Vancouver

Zhu T. Research on Urban Sound Classification based on ConvNeXt-FECA Model. Frontiers in Computing and Intelligent Systems. 2025;13(3):39-45. doi:10.54097/bha9rp62

BibTeX
@article{Zhu2025,
  author = {Zhu, Tianxiang},
  title = {Research on Urban Sound Classification based on ConvNeXt-FECA Model},
  journal = {Frontiers in Computing and Intelligent Systems},
  year = {2025},
  volume = {13},
  number = {3},
  pages = {39--45},
  doi = {10.54097/bha9rp62}
}
Kostenlos starten →