用教师模型指导混淆类别，提升小样本声学场景分类精度
Data Efficient Acoustic Scene Classification using Teacher-Informed Confusing Class Instruction
- 用混音数据增强和通道数缩减降低模型复杂度
- 在5%训练数据下仍达47.97%准确率，100%数据下达62.21%
- 适合资源受限的实时声学场景识别应用
本文介绍了SNTL-NTU团队在DCASE 2024挑战赛任务1——低复杂度高效声学场景分类中的参赛方案。针对不同规模的训练集，提出三种系统：小样本时通过减少基通道数降低模型复杂度，并采用mixup数据增强提升样本多样性；大样本时利用FocusNet提供混淆类信息，指导多个Patchout faSt Spectrogram Transformer（PaSST）模型与原始采样率44.1kHz的基线模型组成的集成模型，再通过知识蒸馏将集成模型压缩至基线学生模型。在TAU Urban Acoustic Scene 2022 Mobile开发集上，三套系统在训练集比例为(100, 50, 25, 10, 5)%时，平均测试准确率分别为(62.21, 59.82, 56.81, 53.03, 47.97)%。
原文摘要 · Abstract (English)
In this technical report, we describe the SNTL-NTU team's submission for Task 1 Data-Efficient Low-Complexity Acoustic Scene Classification of the detection and classification of acoustic scenes and events (DCASE) 2024 challenge. Three systems are introduced to tackle training splits of different sizes. For small training splits, we explored reducing the complexity of the provided baseline model by reducing the number of base channels. We introduce data augmentation in the form of mixup to increase the diversity of training samples. For the larger training splits, we use FocusNet to provide confusing class information to an ensemble of multiple Patchout faSt Spectrogram Transformer (PaSST) models and baseline models trained on the original sampling rate of 44.1 kHz. We use Knowledge Distillation to distill the ensemble model to the baseline student model. Training the systems on the TAU Urban Acoustic Scene 2022 Mobile development dataset yielded the highest average testing accuracy of (62.21, 59.82, 56.81, 53.03, 47.97)% on split (100, 50, 25, 10, 5)% respectively over the three systems.
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。