There You Are! Automated Detection of Indris' Songs on Features Extracted from Passive Acoustic Recordings

Windy events detection in big bioacoustics datasets using a pre-trained Convolutional Neural Network

Passive Acoustic Monitoring (PAM), which involves using autonomous record units for studying wildlife behaviour and distribution, often requires handling big acoustic datasets collected over extended periods. While these data offer invaluable insights about wildlife, their analysis can present challenges in dealing with geophonic sources. A major issue in the process of detection of target sounds is represented by wind-induced noise. This can lead to false positive detections, i.e., energy peaks due to wind gusts misclassified as biological sounds, or false negative, i.e., the wind noise masks the presence of biological sounds. Acoustic data dominated by wind noise makes the analysis of vocal activity unreliable, thus compromising the detection of target sounds and, subsequently, the interpretation of the results. Our work introduces a straightforward approach for detecting recordings affected by windy events using a pre-trained convolutional neural network. This process facilitates identifying wind-compromised data. We consider this dataset pre-processing crucial for ensuring the reliable use of PAM data. We implemented this preprocessing by leveraging YAMNet, a deep learning model for sound classification tasks. We evaluated YAMNet as-is ability to detect wind-induced noise and tested its performance in a Transfer Learning scenario by using our annotated data from the Stony Point Penguin Colony in South Africa. While the classification of YAMNet as-is achieved a precision of 0.71, and recall of 0.66, those metrics strongly improved after the training on our annotated dataset, reaching a precision of 0.91, and recall of 0.92, corresponding to a relative increment of >28 %. Our study demonstrates the promising application of YAMNet in the bioacoustics and ecoacoustics fields, addressing the need for wind-noise-free acoustic data. We released an open-access code that, combined with the efficiency and peak performance of YAMNet, can be used on standard laptops for a broad user base.

Isochrony as ancestral condition to call and song in a primate

Animal songs differ from calls in function and structure, and have comparative and translational value, showing similarities to human music. Rhythm in music is often distributed in quantized classes of intervals known as rhythmic categories. These classes have been found in the songs of a few nonhuman species but never in their calls. Are rhythmic categories song-specific, as in human music, or can they transcend the song-call boundary? We analyze the vocal displays of one of the few mammals producing both songs and call sequences: Indri indri. We test whether rhythmic categories (a) are conserved across songs produced in different contexts, (b) exist in call sequences, and (c) differ between songs and call sequences. We show that rhythmic categories occur across vocal displays. Vocalization type and function modulate deployment of categories. We find isochrony (1:1 ratio, like the rhythm of a ticking clock) in all song types, but only advertisement songs show three rhythmic categories (1:1, 1:2, 2:1 ratios). Like songs, some call types are also isochronous. Isochrony is the backbone of most indri vocalizations, unlike human speech, where it is rare. In indri, isochrony underlies both songs and hierarchy-less call sequences and might be ancestral to both.

Pied tamarins change their vocal behavior in response to noise levels in the largest city in the Amazon

Many animal species depend on sound to communicate with conspecifics. However, human-generated (anthropogenic) noise may mask acoustic signals and so disrupt behavior. Animals may use various strategies to circumvent this, including shifts in the timing of vocal activity and changes to the acoustic parameters of their calls. We tested whether pied tamarins (Saguinus bicolor) adjust their vocal behavior in response to city noise. We predicted that both the probability of occurrence and the number of long calls would increase in response to anthropogenic noise and that pied tamarins would temporally shift their vocal activity to avoid noisier periods. At a finer scale, we anticipated that the temporal parameters of tamarin calls (e.g., call duration and syllable repetition rate) would increase with noise amplitude. We collected information on the acoustic environment and the emission of long calls in nine wild pied tamarin groups in Manaus, Brazil. We found that the probability of long-call occurrence increased with higher levels of anthropogenic noise, though the number of long calls did not. The number of long calls was related to the time of day and the distance from home range borders-a proxy for the distance to neighboring groups. Neither long-call occurrence nor call rate was related to noise levels at different times of day. We found that pied tamarins decreased their syllable repetition rate in response to anthropogenic noise. Long calls are important for group cohesion and intergroup communication. Thus, it is possible that the tamarins emit one long call with lower syllable repetition, which might facilitate signal reception. The occurrence and quantity of pied tamarin' long calls, as well as their acoustic proprieties, seem to be governed by anthropogenic noise, time of the day, and social mechanisms such as proximity to neighboring groups.

An integrated passive acoustic monitoring and deep learning pipeline for black-and-white ruffed lemurs (Varecia variegata) in Ranomafana National Park, Madagascar

The urgent need for effective wildlife monitoring solutions in the face of global biodiversity loss has resulted in the emergence of conservation technologies such as passive acoustic monitoring (PAM). While PAM has been extensively used for marine mammals, birds, and bats, its application to primates is limited. Black-and-white ruffed lemurs (Varecia variegata) are a promising species to test PAM with due to their distinctive and loud roar-shrieks. Furthermore, these lemurs are challenging to monitor via traditional methods due to their fragmented and often unpredictable distribution in Madagascar's dense eastern rainforests. Our goal in this study was to develop a machine learning pipeline for automated call detection from PAM data, compare the effectiveness of PAM versus in-person observations, and investigate diel patterns in lemur vocal behavior. We did this study at Mangevo, Ranomafana National Park by concurrently conducting focal follows and deploying autonomous recorders in May-July 2019. We used transfer learning to build a convolutional neural network (optimized for recall) that automated the detection of lemur calls (57-h runtime; recall = 0.94, F1 = 0.70). We found that PAM outperformed in-person observations, saving time, money, and labor while also providing re-analyzable data. Using PAM yielded novel insights into V. variegata diel vocal patterns; we present the first published evidence of nocturnal calling. We developed a graphic user interface and open-sourced data and code, to serve as a resource for primatologists interested in implementing PAM and machine learning. By leveraging the potential of this pipeline, we can address the urgent need for effective primate population surveys to inform conservation strategies.

Bioacoustic monitoring to determine addiction levels of primates to the human sphere: A feasibility study on Japanese macaques

Some nonhuman primate species, whose original habitats have been reclaimed by artificial activities, have acquired boldness toward humans which is evident based on the diminished frequency of escape behaviors. Eventually, such species have become regular users of human settlements, and are referred to as "urban primates." Considering this, we developed a noninvasive technique based on bioacoustics to provide a transparent assessment of troop addiction levels in anthropogenic environments, which are determined by the dependence on agricultural crops and human living sphere for their diets and daily ranging, respectively. We attempted to quantify the addiction levels based on the boldness of troops when raiding settlements, characterized by a "landscape of fear" because of the presence of humans as predators. We hypothesized that the boldness of troops could be measured using two indices: the frequency of raiding events on settlements and the amount of time spent there. For hypothesis testing, we devised an efficient method to measure these two indices using sound cues (i.e., spontaneous calls) for tracing troop movements that are obtainable throughout the day from most primate species (e.g., contact calls). We conducted a feasibility study of this assessment procedure, targeting troops of Japanese macaques (Macaca fuscata). For this study, we collected 346 recording weeks of data using autonomous recorders from 24 troops with different addiction levels during the nonsnowy seasons. The results demonstrated that troops that reached the threshold level, at which radical interventions including mass culling of troop members is officially permitted, could be readily identified based on the following behavioral characteristics: troop members raiding settlements two or three times per week and mean time spent in settlements per raiding event exceeding 0.4 h. Thus, bioacoustic monitoring could become a valid option to ensure the objectivity of policy judgment in urban primate management.

Bioacoustic characterization of the black-and-white ruffed lemur (Varecia variegata) vocal repertoire

Ruffed lemurs (Varecia spp.) exhibit a unique suite of behavioral traits compared to other lemur species, which includes their fluid fission-fusion social dynamics, communal rearing of parked litters, and pronounced frugivory in their humid rainforest habitats. Given these traits, and the dense rainforests they inhabit, vocal communication may be key to maintaining social cohesion, coordinating infant care, and/or defending their high-quality food resources. Indeed, they are known for their raucous 'roar-shriek' calls. However, there has been surprisingly little research on vocal communication in Varecia species and only two previously published repertoires, both of which were qualitative descriptions of their calls. In this study, we quantitatively examined the vocal repertoire of wild black-and-white ruffed lemurs (Varecia variegata) at Mangevo, Ranomafana National Park, Madagascar. We characterized 11 call types using 33 bioacoustic parameters related to frequency, duration, tonality, and composition. We also used discriminant function analysis and hierarchical clustering to quantitatively and objectively classify call types within the black-and-white ruffed lemur vocal repertoire. The repertoire consists of both monosyllabic and multisyllabic calls that are individually given or emitted in contagious choruses. Eight of the 11 calls were also used in combination or in larger multi-call sequences. The discriminant function analysis correctly assigned call types with 87% success, though this varied greatly by call type (1-65%). Hierarchical clustering identified 3-4 robust clusters, indicating low clustering structure in the data and suggesting that V. variegata exhibits a graded vocal repertoire. Future work should consider the environmental and behavioral contexts in which calls are used to better understand the function of these call types and combinations.

Editorial: Recent Advances in Animal Cognition and Ethology

Animal cognition and ethology, the scientific study of animal behaviour, have long captivated the human imagination [...].

Singing more, singing harsher: occurrence of nonlinear phenomena in a primate' song

Nonlinear phenomena (NLP) in animal vocalizations arise from irregularities in the oscillation of the vocal folds. Various non-mutually exclusive hypotheses have been put forward to explain the occurrence of NLP, from adaptive to physiological ones. Non-human primates often display NLP in their vocalizations, yet the communicative role of these features, if any, is still unclear. We here investigate the occurrence of NLP in the song of a singing primate, the indri (Indri indri), testing for the effect of sex, age, season, and duration of the vocal display on their emission. Our results show that NLP occurrence in indri depends on phonation, i.e., the cumulative duration of all the units emitted by an individual, and that NLP have higher probability to be emitted in the later stages of the song, probably due to the fatigue indris may experience while singing. Furthermore, NLP happen earlier in the vocal display of adult females than in that of the adult males, and this is probably due to the fact that fatigue occurs earlier in the former because of a greater contribution within the song. Our findings suggest, therefore, that indris may be subjected to physiological constraints during the singing process which may impair the production of harmonic sounds. However, indris may still benefit from emitting NLP by strengthening the loudness of their signals for better advertising their presence to the neighboring conspecific groups.