Automatic acoustic detection of birds through deep learning: The first Bird Audio Detection challenge

By Dan Stowell, Yannis Stylianou, Mike Wood, Hanna Pamula, Hervé Glotin. Methods in Ecology and Evolution, 2018

372 citations recorded by the source corpus.

Assessing the presence and abundance of birds is important for monitoring specific species as well as overall ecosystem health. Many birds are most readily detected by their sounds, and thus, passive acoustic monitoring is highly appropriate. Yet acoustic monitoring is often held back by practical limitations such as the need for manual configuration, reliance on example sound libraries, low accuracy, low robustness, and limited ability to generalise to novel acoustic conditions. Here, we report outcomes from a collaborative data challenge. We present new acoustic monitoring datasets, summarise the machine learning techniques proposed by challenge teams, conduct detailed performance evaluation, and discuss how such approaches to detection can be integrated into remote monitoring projects. Multiple methods were able to attain performance of around 88% area under the receiver operating characteristic (ROC) curve (AUC), much higher performance than previous general‐purpose methods. With modern machine learning, including deep learning, general‐purpose acoustic bird detection can achieve very high retrieval rates in remote monitoring data, with no manual recalibration, and no pretraining of the detector for the target species or the acoustic conditions in the target environment.

Subfields: Developmental Biology, Signal Processing

View Paper: https://www.semanticscholar.org/paper/3e3165f06f3334267f1fcb4a018ba27f17b622d8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Developmental Biology

In Signal Processing

Citations in the corpus

Computational bioacoustics with deep learning: a review and roadmap (2021, background): “It is especially beneficial if the testing set represents not just unseen data items but novel conditions, to better estimate the true generalisability of the system (Stowell et al., 2019b).”
Self-supervised audio representation learning for mobile devices (2019, methodology): “Finally, we use two datasets released in the context of the recent DCASE2018 Challenge, Bird Audio Detection [39] and TUT Urban Acoustic Scenes 2018 [25], which contains labeled audio samples from 10 different urban environments.”
Multimodal Self-Supervised Learning of General Audio Representations (2021, positive): “Two tasks are taken from the DCASE2018 challenge: acoustic scenes classiﬁcation [32] and birdsong detection [33].”
Chirping up the Right Tree: Incorporating Biological Taxonomies into Deep Bioacoustic Classifiers (2020, background): “In this context, two open-access data science challenges named LifeCLEF [7] and DCASE Bird Audio Detection [8] have concluded that deep convolutional networks (convnets) achieve state-of-the-art results in bird species classification [9].”
Perspectives in machine learning for wildlife conservation (2021, background): “nals in a wide variety of acoustic environments (67).”
Self-Supervised Speech Representation Learning: A Review (2022, background): “Last, [116] puts together five datasets (MUSAN [245], Bird Audio Detection [246], Speech Commands [247], Spoken Language Identification [248], and TUT Urban Acoustic Scenes”
WILDS: A Benchmark of in-the-Wild Distribution Shifts (2020, neutral): “…using audio sensors to monitor animals that are easier heard than seen such as primates, birds, and marine mammals (Crunchant et al., 2020; Stowell et al., 2019; Shiu et al., 2020), and using static sonar to count fish underwater to help maintain sustainable fishing industries (Pipal et…”
Contrastive Learning of General-Purpose Audio Representations (2020, methodology): “For animal vocalizations, we use the Bird Song Detection (BSD) dataset [30] from DCASE 2018 Challenge to solve a binary classification problem.”
Machine learning and deep learning—A review for ecologists (2022, positive): “…2019 ) or camera (trap) images (Aodha et al., 2018 ; Beery et al., 2020; Fairbrass et al., 2018 ; Ferreira et al., 2020 ; Fritzler et al., 2017; Lasseck, 2018 ; Mäder et al., 2021; Norouzzadeh et al., 2021; Stowell et al., 2018 ; Tabak et al., 2019 ; Van Horn et al., 2018 ; Willi et al., 2019 ).”
Robust sound event detection in bioacoustic sensor networks (2019, background): “It also shows, as stated in the introduction, that the task of avian flight call detection at the fine time scale of isolated acoustic events is fundamentally different from the task of “bird detection in audio”, as formulated by [68] at the scale of ten seconds; and that state-of-the-art systems in”