English

Improving Acoustic Scene Classification in Low-Resource Conditions

Audio and Speech Processing 2025-04-29 v2 Sound

Abstract

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.

Keywords

Cite

@article{arxiv.2412.20722,
  title  = {Improving Acoustic Scene Classification in Low-Resource Conditions},
  author = {Zhi Chen and Yun-Fei Shao and Yong Ma and Mingsheng Wei and Le Zhang and Wei-Qiang Zhang},
  journal= {arXiv preprint arXiv:2412.20722},
  year   = {2025}
}

Comments

Copyright 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component

R2 v1 2026-06-28T20:51:41.491Z