Kaggle: BirdCLEF 2022 Identify bird calls in soundscapes.

Role: Leader of the team.
Designed two phases (detect & classify) to identify birds species from sound segment; Applied Audio Spectrogram Transformer (AST), Vision Transformer (ViT), AlexNet, CNN-RNN network as backbone to both detect whether bird sound exists in segment and which kinds they are.

Geng Li
Geng Li
Postgraduate of Computer Science

My research interests include deep learning, few-shot learning, meta-learning.