用轻量架构与渐进剪枝，实现数据少、算力低场景下的语音场景分类新突破。
Data-Efficient Low-Complexity Acoustic Scene Classification via Distilling and Progressive Pruning
- 设计可重参数的多卷积分支轻量模型Rep-Mobile，兼顾性能与效率。
- 结合知识蒸馏与渐进剪枝，在TAU数据集上达当前最佳（SOTA）效果。
- 适合资源受限设备部署，尤其适用于标注数据稀缺的真实场景。
声学场景分类（ASC）旨在将录音划分到预定义的声学场景类别中。然而在真实应用中，系统常面临设备差异、计算资源有限及标注数据不足等问题。为此，本文提出一种高效且低复杂度的ASC系统，采用新型模型架构与优化训练策略。首先，设计名为Rep-Mobile的轻量级架构，融合多卷积分支并支持推理时重参数化，相比其他模型在更低计算开销下表现更优。其次，引入知识蒸馏策略，并对比不同架构教师模型的数据效率。最后，提出渐进式剪枝方法，通过多次小幅度剪枝提升模型性能，优于单次剪枝。在TAU数据集上的实验表明，结合Rep-Mobile与上述策略，所提系统达到当前最优（SOTA）结果，并在DCASE2024挑战赛中以显著优势夺得第一名。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。