Fan Meng’s research while affiliated with Southwest Forestry University and other places

... Considering together, we proposed a new classifier combining CNN and GRU and achieved good classification results in the song recognition of western blackcrested gibbons in the Ailao Mountains. A third issue is the training of neural networks on acoustic datasets that contain very few vocalization examples of various species that could lead to overfitting (Hawkins, 2004) (e.g., small group sizes due to inaccessible habitats or threatened species) and interference from noise can affect experimental accuracy (Al-Ali et al., 2017;Zhou et al., 2022;Zhou et al., 2022). We have few Western black-crested gibbon song data and they are all from passive acoustic monitoring systems, which also lead to essential environmental noise. ...

Reference:

Methods for processing and analyzing passive acoustic monitoring data: An example of song recognition in western black-crested gibbons