Construction and improvements of bird songs' classification system

Detection of bird species with bird songs is a challenging and meaningful task. Two scenarios are presented in BirdCLEF challenge this year, which are monophone and soundscape. We trained convolutional neural network with both spectrograms extracted from recordings and additionally provided metadata. Focusing on the soundscape situation, we applied bird event detection to reduce false alarm. Besides, we rescored the retrievals using masks which are designed for all species being identified. In addition, context information was also taken into consideration in our system. Our system was evaluated in BirdCLEF 2018 and we achieved an official mean average precision (MAP) score of 0.6548 for monophone classification without background bird songs and 0.5882 for identification with background bird songs. For soundscape, we achieved 0.1196 in classification mean average precision (C-MAP).

Duke Scholars

Author Ming Li DKU Faculty