Acoustic domain mismatch compensation in bird audio detection

Detecting bird calls in audio is an important task for automatic wildlife monitoring, as well as in citizen science and audio library management. This paper presents front-end acoustic enhancement techniques to handle the acoustic domain mismatch problem in bird detection. A time-domain cross-condition data augmentation (TCDA) method is first proposed to enhance the domain coverage of a fixed training dataset. Then, to eliminate the distortion of stationary noise and enhance the transient events, we investigate a per-channel energy normalization (PCEN) to automatic control the gain of every subband in the mel-frequency spectrogram. Furthermore, a harmonic percussive source separation is investigated to extract robust percussive representations of bird call to alleviate the acoustic mismatch. Our experiments are performed on the Bird Audio Detection Task of the IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events 2018. Extensive results show that the proposed TCDA leads to a relative 5.02% AUC improvements on mismatch conditions. And also on the cross-domain test set, the proposed percussive features (RPFs), and these RPFs with PCEN significantly improve the baseline with conventional log mel-spectrogram features from 81.79% AUC to 84.46% and 88.68%, respectively. Moreover, we find that combing different front-end features can further improve the system performances.