arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1611.09526cs.SDcs.AI
收藏

使用声学信号的深度学习学习滤波器组

Learning Filter Banks Using Deep Learning For Acoustic Signals

Bosch(博世)

Shuhui Qu, Juncheng Li, Wei Dai, Samarjit Das

摘要:

为声事件识别任务设计合适的特征是一个活跃的研究领域。表达性特征应该既能提高任务的表现,又能被解释。目前,基于领域知识的启发式设计的特征需要大量的手工制作,而通过深度网络提取的特征很难被人类解释。在这项工作中,我们探讨了经验指导的学习方法设计声学功能。这是一种结合领域知识和纯数据驱动特征设计的新的混合方法。基于对数梅尔滤波器组的过程,设计了滤波器组学习层。我们将这一层与卷积神经网络(CNN)模型连接起来。在训练网络后,提取滤波器组学习层的权值,以便于声学特征的设计。我们平滑学习层的训练权重,并在滤波器组学习层重新初始化它作为音频特征提取器。对于基于Urban-sound 8 K数据集的环境声音识别任务,与固定特征提取器(对数Mel滤波器组)相比,经验引导学习导致2%的准确率提高。新的滤波器组的形状被可视化和解释,以证明特征设计过程的有效性。

英文摘要:

Designing appropriate features for acoustic event recognition tasks is an active field of research. Expressive features should both improve the performance of the tasks and also be interpret-able. Currently, heuristically designed features based on the domain knowledge requires tremendous effort in hand-crafting, while features extracted through deep network are difficult for human to interpret. In this work, we explore the experience guided learning method for designing acoustic features. This is a novel hybrid approach combining both domain knowledge and purely data driven feature designing. Based on the procedure of log Mel-filter banks, we design a filter bank learning layer. We concatenate this layer with a convolutional neural network (CNN) model. After training the network, the weight of the filter bank learning layer is extracted to facilitate the design of acoustic features. We smooth the trained weight of the learning layer and re-initialize it in filter bank learning layer as audio feature extractor. For the environmental sound recognition task based on the Urban- sound8K dataset, the experience guided learning leads to a 2% accuracy improvement compared with the fixed feature extractors (the log Mel-filter bank). The shape of the new filter banks are visualized and explained to prove the effectiveness of the feature design process.

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。

↑