AviaNZ: A future‐proofed program for annotation and recognition of animal sounds in long‐time field recordings

Abstract

The routine collection of long‐time acoustic recordings of animals in the field presents new challenges in data analysis. While many terabytes of data are collected annually, effective use of this noisy, highly variable data require skilled humans to manually identify calls. While computer programs to automatically analyse these recordings are becoming available, it is important that they are user‐friendly and easy‐to‐use, so that everybody – citizen scientists, wildlife managers, researchers – can take advantage of them, and that they keep the human in the loop so analyses carried out this year are comparable both to manual call counts from the past, and more accurate automated analyses performed in the future. We present the AviaNZ program, which is designed to achieve these goals: the software includes methods for simple, rapid manual annotation of recordings, denoising and segmentation methods, and a training procedure by which the user can prepare their own filters to automatically recognize individual species. The software can run in batch mode, automatically processing folders of field recordings, and then present the outputs to enable the quick and easy review of the results. Finally, the outputs are presented in a variety of spreadsheets to enable different statistical analyses to be performed. We describe the various workflows of manually and semi‐automatically processing sound files, annotating them to train automatic filters, using those filters in batch mode, and how the software facilitates rapid evaluation of the automated analysis. A demonstration of the software, comparing manual and automatic detection of calls of the little spotted kiwi Apteryx owenii is given. It shows that while the automatic detection does produce false positives, human correction of these is far faster than manual review of the whole sound file. AviaNZ is a freely available open‐source standalone program. Our experience shows that it can be used by anybody quickly and easily. However, for experienced users it is easily customizable and extendable. By enabling everybody involved with acoustic bird recording to quickly and easily analyse their own data, while future‐proofing it by keeping the human in the loop, we are enabling acoustic field recordings to meet their potential.

Acoustic localization of terrestrial wildlife: Current practices and future opportunities

“…Table describes software used for sound processing in the literature reviewed, but many other bioacoustics signal processing techniques are available. For instance, some recently released programs such as Acoular (Sarradj & Herold, 2017), warbleR (Araya‐Salas & Smith‐Vidaurre, 2017), and AviaNZ (Marsland, Priyadarshani, Juodakis, & Castro, 2019) were not used in the literature reviewed here, but we anticipate their use will be helpful for future practitioners of acoustic localization. For a more complete listing of sound processing techniques and software packages, see Priyadarshani, Marsland, & Castro (2018).…”

“…Comparing this detection method to manual review of a 2‐hr long recording, Ethier and Wilson (2019) found that the automated method successfully detected all manual annotations as well as picking up some detections that were too faint to be annotated by manual review. Automated methods are attractive due to their scalability to many hours of recording (Darras et al, 2019; Marsland et al, 2019), but calibration of these methods can be time‐consuming and may require expert knowledge (Priyadarshani, Marsland, et al, 2018). The number of detections generated by automated methods was as many as 2.7 million (Ethier & Wilson, 2019).…”

Precision as a metric for acoustic survey design using occupancy or spatial capture-recapture

“…Data was processed in the AviaNZ software (Marsland et al, 2019). In the automated process, the software was first trained on a small amount of manually annotated data from the same location, collected in September 2018.…”

Detección automatizada de cantos de aves continúa siendo un desafío: el caso de warbleR y Megascops centralis (búho del Chocó)

“…De manera simultánea y con el fin de alivianar la carga para las personas, se han perpetrado diversos esfuerzos alrededor del mundo por automatizar los procesos de detección y clasificación de señales acústicas (Aide et al, 2013;Ovaskainen et al, 2018;Sethi et al, 2020) . Entre estos esfuerzos podemos encontrar varios programas informáticos como ARBIMON-II (Sieve Analytics, 2015), AviaNZ (Marsland et al, 2019), monitoR (Katz et al, 2016) y warbleR (Araya-Salas & Smith-Vidaurre, 2018).…”