|
发表于 2023-6-25 21:53:20
|
显示全部楼层
[赞][赞],想起我一个师兄的一篇文章和作者想法类似,主要就是将时间序列按周期切片,然后叠加成2D数据,继而对其做后续特征提取与处理,文章如下:X. Zhang, A. Chen, G. Zhou, et al., Spectrogram-frame linear network and continuous frame sequence for bird sound classification, Ecol. Inform. 54 (2019) 101009, http://dx.doi.org/10.1016/j.ecoinf.2019.101009. |
|