EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Multi-Branch BiLSTM with Multi-Head Self-Attention for Suspicious Sound Recognition

Shehu Mohammed Yusuf, Hamza Saidu, Sani Saleh Saminu

Journal of Computing Theories and Applications · 12.05.2026 · 3 (4) · 582-596

DOI: 10.62411/jcta.15777 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Computing Theories and Applications, online erschienen am 12.05.2026. Verfasst von Shehu Mohammed Yusuf und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Suspicious urban sound recognition is a critical component of intelligent public safety and urban monitoring systems, enabling the automated identification of anomalous acoustic events such as gunshots, sirens, and other security-sensitive sounds. However, existing deep learning approaches often struggle to simultaneously capture long-range temporal dependencies and global contextual relationships, particularly under noisy and acoustically complex urban conditions. This limitation can reduce reliability in safety-critical scenarios where missed detections carry significant risk. To address these challenges, this study proposes a Multi-Branch Bidirectional Long Short-Term Memory (BiLSTM) framework with Multi-Head Self-Attention (MHSA) for enhanced sequential and contextual feature modeling. Mel-frequency cepstral coefficients (MFCCs) are extracted from a curated subset of the UrbanSound8K dataset, comprising five suspicious sound classes, and used as input to the proposed architecture. The multi-branch design enables complementary temporal representations, while the self-attention mechanism provides lightweight contextual weighting of BiLSTM outputs. Experimental results demonstrate that the proposed model achieves a test accuracy of 95.59%, outperforming conventional Dense and LSTM-based baseline models under identical experimental settings. An ablation study further confirms the contribution of multi-branch integration and attention-based enhancement to overall performance. Class-wise evaluation reveals consistently high recall across all sound categories, particularly for safety-critical classes such as gunshots and sirens. These findings indicate that the proposed framework provides robust and reliable performance, making it suitable for real-time smart city surveillance and public safety applications.

Zitieren

APA

Yusuf, S. M., Saidu, H., & Saminu, S. S. (2026). A Multi-Branch BiLSTM with Multi-Head Self-Attention for Suspicious Sound Recognition. Journal of Computing Theories and Applications, 3(4), 582-596. https://doi.org/10.62411/jcta.15777

Vancouver

Yusuf SM, Saidu H, Saminu SS. A Multi-Branch BiLSTM with Multi-Head Self-Attention for Suspicious Sound Recognition. Journal of Computing Theories and Applications. 2026;3(4):582-596. doi:10.62411/jcta.15777

BibTeX
@article{Yusuf2026,
  author = {Yusuf, Shehu Mohammed and Saidu, Hamza and Saminu, Sani Saleh},
  title = {A Multi-Branch BiLSTM with Multi-Head Self-Attention for Suspicious Sound Recognition},
  journal = {Journal of Computing Theories and Applications},
  year = {2026},
  volume = {3},
  number = {4},
  pages = {582--596},
  doi = {10.62411/jcta.15777}
}
Kostenlos starten →