Low-Complexity Acoustic Scene Classification Using Parallel Attention-Convolution Network
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913387825332224 |
|---|---|
| author | Li, Yanxiong Tan, Jiaxin Chen, Guoqing Li, Jialong Si, Yongjie He, Qianhua |
| author_facet | Li, Yanxiong Tan, Jiaxin Chen, Guoqing Li, Jialong Si, Yongjie He, Qianhua |
| contents | This work is an improved system that we submitted to task 1 of DCASE2023 challenge. We propose a method of low-complexity acoustic scene classification by a parallel attention-convolution network which consists of four modules, including pre-processing, fusion, global and local contextual information extraction. The proposed network is computationally efficient to capture global and local contextual information from each audio clip. In addition, we integrate other techniques into our method, such as knowledge distillation, data augmentation, and adaptive residual normalization. When evaluated on the official dataset of DCASE2023 challenge, our method obtains the highest accuracy of 56.10% with parameter number of 5.21 kilo and multiply-accumulate operations of 1.44 million. It exceeds the top two systems of DCASE2023 challenge in accuracy and complexity, and obtains state-of-the-art result. Code is at: https://github.com/Jessytan/Low-complexity-ASC. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_08119 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Low-Complexity Acoustic Scene Classification Using Parallel Attention-Convolution Network Li, Yanxiong Tan, Jiaxin Chen, Guoqing Li, Jialong Si, Yongjie He, Qianhua Audio and Speech Processing Sound This work is an improved system that we submitted to task 1 of DCASE2023 challenge. We propose a method of low-complexity acoustic scene classification by a parallel attention-convolution network which consists of four modules, including pre-processing, fusion, global and local contextual information extraction. The proposed network is computationally efficient to capture global and local contextual information from each audio clip. In addition, we integrate other techniques into our method, such as knowledge distillation, data augmentation, and adaptive residual normalization. When evaluated on the official dataset of DCASE2023 challenge, our method obtains the highest accuracy of 56.10% with parameter number of 5.21 kilo and multiply-accumulate operations of 1.44 million. It exceeds the top two systems of DCASE2023 challenge in accuracy and complexity, and obtains state-of-the-art result. Code is at: https://github.com/Jessytan/Low-complexity-ASC. |
| title | Low-Complexity Acoustic Scene Classification Using Parallel Attention-Convolution Network |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2406.08119 |