arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.08183cs.SDcs.LGeess.AS
收藏

用于音频分类的半监督深度学习算法比较

Comparison of semi-supervised deep learning algorithms for audio classification

IRIT(法国图卢兹计算机科学研究所);University of Toulouse(图卢兹大学);CNRS(法国国家科学研究中心);Artificial and Natural Intelligence Toulouse Institute (ANITI)(图卢兹人工智能与自然智能研究所(ANITI))

Léo Cances, Etienne Labbé, Thomas Pellegrini

摘要:

在这篇文章中,我们采用了五种最近的SSL方法来完成音频分类任务。前两种方法,即深度协同训练(DCT)和均值教师(MT),涉及两个协作的神经网络。其他三种算法,称为MixMatch(MM),ReMixMatch(RMM)和FixMatch(FM),是主要依赖于数据增强策略的单模型方法。在我们所有的实验中使用Wide-ResNet-28-2架构,10%的标记数据和剩余的90%作为未标记数据进行训练,我们首先在三个标准基准音频数据集上比较五种方法的出错率:环境声音分类(ESC-10),UrbanSound 8 K(UBS 8 K)和Google Speech Commands(GSC)。在所有情况下,除了一种情况下,MM,RMM,FM优于MT和DCT显着,MM和RMM是最好的方法在大多数实验。在UBS 8 K和GSC上,MM分别实现了18.02%和3.25%的出错率(ER),优于使用100%可用标记数据训练的模型,分别达到23.29%和4.94%。RMM在ESC-10上取得了最好的结果(12.00% ER),其次是FM,达到13.33%。其次,我们探索了将MM和RMM中使用的混合增强添加到DCT,MT和FM中。在几乎所有的情况下,混淆带来了持续的收益。例如,在GSC上,FM达到4.44%和3.31% ER,没有和有混淆。我们的PyTorch代码将在https://github上以书面形式提供。com/ Labbe ti/ SSLH.

英文摘要:

In this article, we adapted five recent SSL methods to the task of audio classification. The first two methods, namely Deep Co-Training (DCT) and Mean Teacher (MT), involve two collaborative neural networks. The three other algorithms, called MixMatch (MM), ReMixMatch (RMM), and FixMatch (FM), are single-model methods that rely primarily on data augmentation strategies. Using the Wide-ResNet-28-2 architecture in all our experiments, 10% of labeled data and the remaining 90% as unlabeled data for training, we first compare the error rates of the five methods on three standard benchmark audio datasets: Environmental Sound Classification (ESC-10), UrbanSound8K (UBS8K), and Google Speech Commands (GSC). In all but one cases, MM, RMM, and FM outperformed MT and DCT significantly, MM and RMM being the best methods in most experiments. On UBS8K and GSC, MM achieved 18.02% and 3.25% error rate (ER), respectively, outperforming models trained with 100% of the available labeled data, which reached 23.29% and 4.94%, respectively. RMM achieved the best results on ESC-10 (12.00% ER), followed by FM which reached 13.33%. Second, we explored adding the mixup augmentation, used in MM and RMM, to DCT, MT, and FM. In almost all cases, mixup brought consistent gains. For instance, on GSC, FM reached 4.44% and 3.31% ER without and with mixup. Our PyTorch code will be made available upon paper acceptance at https:// github. com/ Labbe ti/ SSLH.

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。

↑