Data-Efficient Low-Complexity Acoustic Scene Classification via Distilling and Progressive Pruning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915275938463744 |
|---|---|
| author | Han, Bing Huang, Wen Chen, Zhengyang Jiang, Anbai Fan, Pingyi Lu, Cheng Lv, Zhiqiang Liu, Jia Zhang, Wei-Qiang Qian, Yanmin |
| author_facet | Han, Bing Huang, Wen Chen, Zhengyang Jiang, Anbai Fan, Pingyi Lu, Cheng Lv, Zhiqiang Liu, Jia Zhang, Wei-Qiang Qian, Yanmin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_20775 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Data-Efficient Low-Complexity Acoustic Scene Classification via Distilling and Progressive Pruning Han, Bing Huang, Wen Chen, Zhengyang Jiang, Anbai Fan, Pingyi Lu, Cheng Lv, Zhiqiang Liu, Jia Zhang, Wei-Qiang Qian, Yanmin Sound Audio and Speech Processing 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. |
| title | Data-Efficient Low-Complexity Acoustic Scene Classification via Distilling and Progressive Pruning |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2410.20775 |