Tampere University of Technology

TUTCRIS Research Portal

Turning wingbeat sounds into spectrum images for acoustic insect classification

Research output: Contribution to journalArticleScientificpeer-review


Original languageEnglish
Pages (from-to)1674-1676
Number of pages3
JournalElectronics Letters
Issue number25
Publication statusPublished - 2017
Publication typeA1 Journal article-refereed


A novel acoustic insect classifier on deep convolutional feature of frequency spectrum images generated by their wingbeat sounds is introduced. By visualising insect wingbeat sound, the proposed method is the first attempt to convert time-series acoustic signal processing to image recognition, which has recently gained significant improvement with convolutional neural networks. Experiments show the better accuracy of the proposed method on the public UCR flying insect datasets compared with the state-of-the-art methods.


  • acoustic imaging, acoustic signal processing, image classification, neural nets, time series, acoustic insect classification, convolutional neural network, deep convolutional feature, frequency spectrum image classification, image recognition, insect wingbeat sound visualization, public UCR flying insect, time-series acoustic signal processing, wingbeat sound tuning

Publication forum classification

Field of science, Statistics Finland