刘炜杰,梁晋华,张 涛.音频场景识别中非对称卷积和知识迁移方法研究[J].电子测量与仪器学报,2021,35(5):168-173 |
音频场景识别中非对称卷积和知识迁移方法研究 |
Investigation on asymmetric convolution and knowledge transferin acoustic scene classification |
|
DOI: |
中文关键词: 音频场景识别 非对称卷积 知识迁移 卷积神经网络 模式识别 |
英文关键词:acoustic scene classification asymmetric convolution knowledge transfer convolutional neural network pattern recognition |
基金项目:天津市研究生科研创新项目(2019YJSS146)资助 |
|
|
摘要点击次数: 824 |
全文下载次数: 3 |
中文摘要: |
针对当前音频场景识别中训练数据量不足的问题,设计了基于知识迁移的非对称卷积声音场景识别系统。 相较于现有
方法利用音频场景识别数据集从头训练网络模型,该系统在其他任务训练好的网络模型上进行调整和训练,从而保留了源领域
的有效信息。 与此同时,该系统针对声学特征的特点,采用了非对称卷积模块来增强网络的特征提取能力。 实验结果为该系统
的准确率相较基准系统提高了 0. 023,并且该系统的卷积核可视化结果观察到的特征纹理更清晰。 结果表明知识迁移可以提
升模型的特征表示能力,与非对称卷积结合能进一步提升系统性能。 |
英文摘要: |
A novel acoustic scene classification (ASC) system based on asymmetric convolution and knowledge transfer is proposed to
address the problem caused by limited ASC datasets. Compared with the existing methods which trained models from scratch, the
proposed system fine-tunes a pretrained model of other tasks to preserve valid information from the source domain. Besides, targeted at
the nature of acoustic features, it adopts asymmetric convolutions to enhance the network capability of feature extraction. Experiments
shows that the proposed system outperforms the baseline system by 0. 023. Besides, as shown in the visualization results of convolutional
filters, textures of the proposed system are more detailed than other methods. The experiment proves that knowledge transfer can boost
model ability of feature representation, and it can further improve system performance by combining with asymmetric convolution. |
查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|