Applicability of VGGish embedding in bee colony monitoring: comparison with MFCC in colony sound classification
Nayan Di, Muhammad Zahid Sharif, Zongwen Hu, Renjie Xue, Baizhong Yu
Abstract
Background: Bee colony sound is a continuous, low-frequency buzzing sound that varies with the environment or the colony's behavior and is considered meaningful. Bees use sounds to communicate within the hive, and bee colony sounds investigation can reveal helpful information about the circumstances in the colony. Therefore, one crucial step in analyzing bee colony sounds is to extract appropriate acoustic feature. Methods: This article uses VGGish (a visual geometry group-like audio classification model) embedding and Mel-frequency Cepstral Coefficient (MFCC) generated from three bee colony sound datasets, to train four machine learning algorithms to determine which acoustic feature performs better in bee colony sound recognition. Results: The results showed that VGGish embedding performs better than or on par with MFCC in all three datasets.