Assessing the performance of a semi‐automated acoustic monitoring system for primates

Abstract

Summary1. Passive acoustic monitoring is frequently used for marine mammals, and more recently it has also become popular for terrestrial species. Key advantages are the monitoring of (1) elusive species, (2) different taxa simultaneously, (3) large temporal and spatial scales, (4) with reduced human presence and (5) with considerable time saving for data processing. However, terrestrial sound environments can be highly complex; they are very challenging when trying to automatically detect and classify vocalizations because of low signal-to-noise ratios. Therefore, most studies have used manual preselection of high-quality sounds to achieve better classification rates. Consequently, most systems have never been validated under realistic field conditions. 2. In this study, we evaluated the performance of a passive acoustic monitoring system for four primate species in the highly noisy rain forest environment of the Ta€ ı National Park, Côte d'Ivoire. We collected 12 851 h of recordings with 20 autonomous recording units and did not preselect high-quality sounds manually. To automatically detect and classify the sounds of interest, we used an automated system built on speaker segmentation, support vector machines and Gaussian mixture models. One hundred and seventy-nine hours of recordings were used for validating the system. 3. The system performed well in detecting the loud calls of Cercopithecus diana and Colobus polykomos with a recall of 50% and 42%, respectively. Recall rates were lower for Pan troglodytes and Procolobus badius. To determine the presence of Cercopithecus diana and Colobus polykomos with a certainty of P > 0Á999, 2 and 7 h of recordings were needed, respectively. For these two species, our automated approach reflected the spatio-temporal distribution of vocalization events well. Despite the seemingly low precision, time investment for the manual removal of false positives in the system's output was only 3Á5% compared to a human collecting and processing the primate vocalization data. 4. The proposed monitoring system is already fully applicable for Cercopithecus diana and Colobus polykomos, whereas it needs further improvement for the other species tested. In principle, it can be applied to any distinctive animal sound and can be implemented for the collection of acoustic data for behavioural, ecological and conservation studies.

Passive acoustic monitoring reveals group ranging and territory use: a case study of wild chimpanzees (Pan troglodytes)

“…The maximum recall for chimpanzee drum sounds with our algorithm was 11 % and precision was 4 %, which was of low performance compared to two monkey calls that were also targeted by the system. However, overall we had results comparable to other studies [19]. Please see Heinicke and colleagues [19] for further details about the algorithm and its performance metrics that were assessed in a separate study.…”

“…However, overall we had results comparable to other studies [19]. Please see Heinicke and colleagues [19] for further details about the algorithm and its performance metrics that were assessed in a separate study.…”

“…A customized algorithm for the automated detection and classification of chimpanzee sounds was used to extract chimpanzee drums from continuous ARU recordings made in the Taï forest [19]. Only chimpanzee drums that were subsequently verified to be true positive detections were included in the final dataset, however; we also included any detections that had been misclassified as chimpanzee drum but were actually long range chimpanzee vocalizations (screams or pant hoots).…”

“…It has been successfully employed for the study of tropical birds [13, 14] and land mammals such as forest elephants [15, 16], Bornean orangutans [17], as well as multi-species systems [18, 19], but one limiting factor in all terrestrial applications continues to be effective automated approaches for mining the PAM data to extract calls of interest. The high variability of many mammalian vocalizations, and complex background noise present in terrestrial ecosystems [20] have hindered the progress of PAM for land mammals, including our closest living relatives, the great apes.…”

Direction-of-arrival estimation of animal vocalizations for monitoring animal behavior and improving estimates of abundance

“…Technological advances hold promise to improve coverage through the adoption of autonomous sensors for the collection of biological data (Porter et al 2009). One type of automated sensor is the autonomous recording unit (ARU) for passive acoustic data collection, which is increasingly being employed for studies on marine mammals (Stafford et al 1998, Laurinolli et al 2003, Bonnel et al 2008, Mouy et al 2012, Rone et al 2012, terrestrial mammals (Heinicke et al 2015), bats (MacSwiney González et al 2008), and birds (Mennill et al 2006, Brandes 2008, Collier et al 2010. ARUs confer several advantages over traditional methods of observation.…”