Improving Acoustic Scene Classification in Low-Resource Conditions
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910919978647552 |
|---|---|
| author | Chen, Zhi Shao, Yun-Fei Ma, Yong Wei, Mingsheng Zhang, Le Zhang, Wei-Qiang |
| author_facet | Chen, Zhi Shao, Yun-Fei Ma, Yong Wei, Mingsheng Zhang, Le Zhang, Wei-Qiang |
| contents | Acoustic Scene Classification (ASC) identifies an environment based on an audio signal. This paper explores ASC in low-resource conditions and proposes a novel model, DS-FlexiNet, which combines depthwise separable convolutions from MobileNetV2 with ResNet-inspired residual connections for a balance of efficiency and accuracy. To address hardware limitations and device heterogeneity, DS-FlexiNet employs Quantization Aware Training (QAT) for model compression and data augmentation methods like Auto Device Impulse Response (ADIR) and Freq-MixStyle (FMS) to improve cross-device generalization. Knowledge Distillation (KD) from twelve teacher models further enhances performance on unseen devices. The architecture includes a custom Residual Normalization layer to handle domain differences across devices, and depthwise separable convolutions reduce computational overhead without sacrificing feature representation. Experimental results show that DS-FlexiNet excels in both adaptability and performance under resource-constrained conditions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_20722 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Improving Acoustic Scene Classification in Low-Resource Conditions Chen, Zhi Shao, Yun-Fei Ma, Yong Wei, Mingsheng Zhang, Le Zhang, Wei-Qiang Audio and Speech Processing Sound Acoustic Scene Classification (ASC) identifies an environment based on an audio signal. This paper explores ASC in low-resource conditions and proposes a novel model, DS-FlexiNet, which combines depthwise separable convolutions from MobileNetV2 with ResNet-inspired residual connections for a balance of efficiency and accuracy. To address hardware limitations and device heterogeneity, DS-FlexiNet employs Quantization Aware Training (QAT) for model compression and data augmentation methods like Auto Device Impulse Response (ADIR) and Freq-MixStyle (FMS) to improve cross-device generalization. Knowledge Distillation (KD) from twelve teacher models further enhances performance on unseen devices. The architecture includes a custom Residual Normalization layer to handle domain differences across devices, and depthwise separable convolutions reduce computational overhead without sacrificing feature representation. Experimental results show that DS-FlexiNet excels in both adaptability and performance under resource-constrained conditions. |
| title | Improving Acoustic Scene Classification in Low-Resource Conditions |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2412.20722 |