Deep learning for detection of bird vocalisations
This work addresses the need for automated bird sound detection to aid researchers, conservationists, and policymakers in monitoring biodiversity, though it is incremental as it builds on existing deep learning methods for audio enhancement.
The paper tackles the problem of detecting bird vocalizations in noisy field recordings by developing a deep autoencoder that maps audio spectrograms to binary masks, achieving fast and minimally supervised processing suitable for large-scale data analysis.
This work focuses on reliable detection of bird sound emissions as recorded in the open field. Acoustic detection of avian sounds can be used for the automatized monitoring of multiple bird taxa and querying in long-term recordings for species of interest for researchers, conservation practitioners, and decision makers. Recordings in the wild can be very noisy due to the exposure of the microphones to a large number of audio sources originating from all distances and directions, the number and identity of which cannot be known a-priori. The co-existence of the target vocalizations with abiotic interferences in an unconstrained environment is inefficiently treated by current approaches of audio signal enhancement. A technique that would spot only bird vocalization while ignoring other audio sources is of prime importance. These difficulties are tackled in this work, presenting a deep autoencoder that maps the audio spectrogram of bird vocalizations to its corresponding binary mask that encircles the spectral blobs of vocalizations while suppressing other audio sources. The procedure requires minimum human attendance, it is very fast during execution, thus suitable to scan massive volumes of data, in order to analyze them, evaluate insights and hypotheses, identify patterns of bird activity that, hopefully, finally lead to design policies on biodiversity issues.