Hierarchical model improves urban environmental sound recognition accuracy
A Hierarchical Method for Environmental Sounds Recognition in Complex Acoustic Scenes
SoundMachine Learning
Summary
Environmental noise detection helps monitor and control city noise. The authors created a two-step approach that first groups sounds into broad categories, then identifies specific types within those groups. Their method uses a special lightweight neural network to better understand time and frequency patterns in sounds. Tests on various datasets and real-world monitoring show their approach is more accurate than previous models while being efficient.
What this means in practice
- •For urban monitoring teams: Increase accuracy and efficiency of city noise monitoring platforms by implementing hierarchical sound recognition models.
- •For audio device manufacturers: Integrate lightweight models in noise-detection devices to reliably classify complex urban environmental sounds with constrained hardware.$Commercial implications: Enables production of affordable, real-time noise monitoring gadgets using efficient hierarchical classifiers.
Authors
Zhouwen Li, Haijun Lin, Bowen Lv, Yupeng Chen
Abstract
Environmental noise identification is essential for noise control, yet conventional single-stage classifiers suffer from class confusion under imbalanced multiclass conditions. This paper proposes a lightweight hierarchical model integrating a Frequency-Time Adaptive Network (FTANet) with a two-stage classification mechanism. FTANet employs parallel asymmetric one-dimensional convolutions to capture temporal dynamics and frequency-band distributions, while adaptive fusion attention (AFA) enhances discriminative acoustic features. In the first stage, FTANet classifies sounds into five coarse-grained categories covering 25 fine-grained classes. In the second stage, samples are routed to the corresponding category-specific classifiers for fine-grained recognition. On a self-constructed dataset, FTANet achieves 95.45% coarse-grained accuracy with only 0.2004M parameters. On UrbanSound8K, it achieves 79.24% mean accuracy and 80.37% mean F1-score in ten-fold evaluation, outperforming compared convolutional models. Field tests on the Tianjin Online Acoustic Environment Monitoring Platform yield 87.94% coarse-grained accuracy and 97.21% conditional fine-grained accuracy for natural sounds correctly routed to C2. The complete hierarchical model achieves 87.18% overall accuracy and 87.40% weighted-average F1-score, demonstrating its feasibility for urban environmental noise monitoring.