English

Data-Efficient Low-Complexity Acoustic Scene Classification via Distilling and Progressive Pruning

Sound 2025-05-08 v1 Audio and Speech Processing

Abstract

The goal of the acoustic scene classification (ASC) task is to classify recordings into one of the predefined acoustic scene classes. However, in real-world scenarios, ASC systems often encounter challenges such as recording device mismatch, low-complexity constraints, and the limited availability of labeled data. To alleviate these issues, in this paper, a data-efficient and low-complexity ASC system is built with a new model architecture and better training strategies. Specifically, we firstly design a new low-complexity architecture named Rep-Mobile by integrating multi-convolution branches which can be reparameterized at inference. Compared to other models, it achieves better performance and less computational complexity. Then we apply the knowledge distillation strategy and provide a comparison of the data efficiency of the teacher model with different architectures. Finally, we propose a progressive pruning strategy, which involves pruning the model multiple times in small amounts, resulting in better performance compared to a single step pruning. Experiments are conducted on the TAU dataset. With Rep-Mobile and these training strategies, our proposed ASC system achieves the state-of-the-art (SOTA) results so far, while also winning the first place with a significant advantage over others in the DCASE2024 Challenge.

Keywords

Cite

@article{arxiv.2410.20775,
  title  = {Data-Efficient Low-Complexity Acoustic Scene Classification via Distilling and Progressive Pruning},
  author = {Bing Han and Wen Huang and Zhengyang Chen and Anbai Jiang and Pingyi Fan and Cheng Lu and Zhiqiang Lv and Jia Liu and Wei-Qiang Zhang and Yanmin Qian},
  journal= {arXiv preprint arXiv:2410.20775},
  year   = {2025}
}

Comments

submitted to ICASSP 2025

R2 v1 2026-06-28T19:37:40.084Z