arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1907.01803cs.LGcs.SDeess.ASstat.ML
收藏

感受场作为深度卷积神经网络的正则化器用于声场景分类

The Receptive Field as a Regularizer in Deep Convolutional Neural Networks for Acoustic Scene Classification

LIT Artificial Intelligence Lab, Johannes Kepler University Linz(林茨约翰内斯·开普勒大学LIT人工智能实验室)

Khaled Koutini, Hamid Eghbal-zadeh, Matthias Dorfer, Gerhard Widmer

摘要:

卷积神经网络(CNN)在许多机器视觉和机器听觉任务中取得了巨大的成功。因此,许多图像识别网络架构已被适配用于音频处理任务。然而,尽管取得了一些成功,其中许多的性能并没有从图像转换到音频域。例如,ResNet和DenseNet等深度架构在图像识别方面的表现明显优于VGG,但在声学场景分类(ASC)等音频处理任务中的表现并不好。在本文中,我们研究了为什么这种强大的架构在ASC中的表现不如简单的模型(例如,VGG)。为此,我们分析了这些CNN的感受野(RF),并证明了RF对模型泛化能力的重要性。使用我们的感受野分析,我们调整了ResNet和DenseNet,实现了最先进的性能,并最终超越了基于VGG的模型。我们介绍了在CNN中调整RF的系统方法,并给出了三个数据集的结果,这些数据集显示了RF随时间和频率维度的变化如何影响模型的性能。我们的实验结果表明,非常小或非常大的RF会导致性能下降,但通过在一定范围内仔细选择适当的RF大小,可以使深度模型很好地泛化。

英文摘要:

Convolutional Neural Networks (CNNs) have had great success in many machine vision as well as machine audition tasks. Many image recognition network architectures have consequently been adapted for audio processing tasks. However, despite some successes, the performance of many of these did not translate from the image to the audio domain. For example, very deep architectures such as ResNet and DenseNet, which significantly outperform VGG in image recognition, do not perform better in audio processing tasks such as Acoustic Scene Classification (ASC). In this paper, we investigate the reasons why such powerful architectures perform worse in ASC compared to simpler models (e.g., VGG). To this end, we analyse the receptive field (RF) of these CNNs and demonstrate the importance of the RF to the generalization capability of the models. Using our receptive field analysis, we adapt both ResNet and DenseNet, achieving state-of-the-art performance and eventually outperforming the VGG-based models. We introduce systematic ways of adapting the RF in CNNs, and present results on three data sets that show how changing the RF over the time and frequency dimensions affects a model's performance. Our experimental results show that very small or very large RFs can cause performance degradation, but deep models can be made to generalize well by carefully choosing an appropriate RF size within a certain range.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑