Low-cost open-source recorders and ready-to-use machine learning approaches provide effective monitoring of threatened species

Passive acoustic monitoring is a powerful tool for monitoring vocally active taxa. Automated signal recognition software reduces the expert time needed for recording analyses and allows researchers and managers to manage large acoustic datasets. The application of state-of-the-art techniques for automated identification, such as Convolutional Neural Networks, may be challenging for ecologists and managers without informatics or engineering expertise. Here, we evaluated the use of AudioMoth — a low-cost and open-source sound recorder — to monitor a threatened and patchily distributed species, the Eurasian bittern (Botaurus stellaris). Passive acoustic monitoring was carried out across 17 potential wetlands in north Spain. We also assessed the performance of BirdNET — an automated and freely available classifier able to identify over 3000 bird species — and Kaleidoscope Pro — a user-friendly recognition software — to detect the vocalizations and the presence of the target species. The percentage of presences and vocalizations of the Eurasian bittern automatically detected by BirdNET and Kaleidoscope Pro software was compared to manual annotations of 205 recordings. The species was effectively recorded up to distances of 801–900 m, with at least 50% of the vocalizations uttered within that distance being manually detected; this distance was reduced to 601–700 m when considering the analyses carried out using Kaleidoscope Pro. BirdNET detected the species in 59 of the 63 (93.7%) recordings with known presence of the species, while Kaleidoscope detected the bittern in 62 recordings (98.4%). At the vocalization level, BirdNet and Kaleidoscope Pro were able to detect between 76 and 78%, respectively, of the vocalizations detected by a human observer. Our study highlights the ability of AudioMoth for detecting the bittern at large distances, which increases the potential of that technique for monitoring the species at large spatial scales. According to our results, a single AudioMoth could be useful for monitoring the species' presence in wetlands of up to 150 ha. Our study proves the utility of passive acoustic monitoring, coupled with BirdNET or Kaleidoscope Pro, as an accurate, repeatable, and cost-efficient method for monitoring the Eurasian bittern at large spatial and temporal scales. Nonetheless, further research should evaluate the performance of BirdNET on a larger number of species, and under different recording conditions (e.g., more closed habitats), to improve our knowledge about BirdNET's ability to perform bird monitoring. Future studies should also aim to develop an adequate protocol to perform effective passive acoustic monitoring of the Eurasian bittern.     

Vocal signature in capybara,Hydrochoerus hydrochaeris

Social groups of capybaras are stable and cohesive. The species’ vocal communication is complex and mediates social interaction. The click call is emitted in a variety of contexts by animals from all age groups, but differs among groups; its attributed function is to keep contact among animals. To evaluate the presence of individual characteristics in the click call of capybaras, we recorded the vocalizations emitted spontaneously by six adults kept either solitary or in groups. We selected and measured the acoustic parameters of 300 click call phrases, 50 per individual. The parameters were submitted to a discriminant function analysis that revealed a classification accuracy of 76.8 %. A General Linear Model analysis revealed significant differences among the six individuals, and post hoc results showed that differences between a given pair were different from those of any other pair. The acoustic parameters that most contributed to discriminate the individual calls were click interval duration and click duration, suggesting that temporal parameters are more important than frequency parameters for individuals’ discrimination. The findings of individual characteristics in the click calls indicate that these vocalizations can be used as vocal signatures during social interactions.     

Adaptive frequency scaled wavelet packet decomposition for frog call classification

Environmental changes have put great pressure on biological systems leading to the rapid decline of biodiversity. To monitor this change and protect biodiversity, animal vocalizations have been widely explored by the aid of deploying acoustic sensors in the field. Consequently, large volumes of acoustic data are collected. However, traditional manual methods that require ecologists to physically visit sites to collect biodiversity data are both costly and time consuming. Therefore it is essential to develop new semi-automated and automated methods to identify species in automated audio recordings. In this study, a novel feature extraction method based on wavelet packet decomposition is proposed for frog call classification. After syllable segmentation, the advertisement call of each frog syllable is represented by a spectral peak track, from which track duration, dominant frequency and oscillation rate are calculated. Then, a k-means clustering algorithm is applied to the dominant frequency, and the centroids of clustering results are used to generate the frequency scale for wavelet packet decomposition (WPD). Next, a new feature set named adaptive frequency scaled wavelet packet decomposition sub-band cepstral coefficients is extracted by performing WPD on the windowed frog calls. Furthermore, the statistics of all feature vectors over each windowed signal are calculated for producing the final feature set. Finally, two well-known classifiers, a k-nearest neighbour classifier and a support vector machine classifier, are used for classification. In our experiments, we use two different datasets from Queensland, Australia (18 frog species from commercial recordings and field recordings of 8 frog species from James Cook University recordings). The weighted classification accuracy with our proposed method is 99.5% and 97.4% for 18 frog species and 8 frog species respectively, which outperforms all other comparable methods.     

Calling at the highway: The spatiotemporal constraint of road noise on Pacific chorus frog communication

Loss of acoustic habitat due to anthropogenic noise is a key environmental stressor for vocal amphibian species, a taxonomic group that is experiencing global population declines. The Pacific chorus frog (Pseudacris regilla) is the most common vocal species of the Pacific Northwest and can occupy human‐dominated habitat types, including agricultural and urban wetlands. This species is exposed to anthropogenic noise, which can interfere with vocalizations during the breeding season. We hypothesized that Pacific chorus frogs would alter the spatial and temporal structure of their breeding vocalizations in response to road noise, a widespread anthropogenic stressor. We compared Pacific chorus frog call structure and ambient road noise levels along a gradient of road noise exposures in the Willamette Valley, Oregon, USA. We used both passive acoustic monitoring and directional recordings to determine source level (i.e., amplitude or volume), dominant frequency (i.e., pitch), call duration, and call rate of individual frogs and to quantify ambient road noise levels. Pacific chorus frogs were unable to change their vocalizations to compensate for road noise. A model of the active space and time (“spatiotemporal communication”) over which a Pacific chorus frog vocalization could be heard revealed that in high‐noise habitats, spatiotemporal communication was drastically reduced for an individual. This may have implications for the reproductive success of this species, which relies on specific call repertoires to portray relative fitness and attract mates. Using the acoustic call parameters defined by this study (frequency, source level, call rate, and call duration), we developed a simplified model of acoustic communication space–time for this species. This model can be used in combination with models that determine the insertion loss for various acoustic barriers to define the impact of anthropogenic noise on the radius of communication in threatened species. Additionally, this model can be applied to other vocal taxonomic groups provided the necessary acoustic parameters are determined, including the frequency parameters and perception thresholds. Reduction in acoustic habitat by anthropogenic noise may emerge as a compounding environmental stressor for an already sensitive taxonomic group.     

Unsupervised classification to improve the quality of a bird song recording dataset

Open audio databases such as Xeno-Canto are widely used to build datasets to explore bird song repertoire or to train models for automatic bird sound classification by deep learning algorithms. However, such databases suffer from the fact that bird sounds are weakly labelled: a species name is attributed to each audio recording without timestamps that provide the temporal localization of the bird song of interest. Manual annotations can solve this issue, but they are time consuming, expert-dependent, and cannot run on large datasets. Another solution consists in using a labelling function that automatically segments audio recordings before assigning a label to each segmented audio sample. Although labelling functions were introduced to expedite strong label assignment, their classification performance remains mostly unknown. To address this issue and reduce label noise (wrong label assignment) in large bird song datasets, we introduce a data-centric novel labelling function composed of three successive steps: 1) time-frequency sound unit segmentation, 2) feature computation for each sound unit, and 3) classification of each sound unit as bird song or noise with either an unsupervised DBSCAN algorithm or the supervised BirdNET neural network. The labelling function was optimized, validated, and tested on the songs of 44 West-Palearctic common bird species. We first showed that the segmentation of bird songs alone aggregated from 10% to 83% of label noise depending on the species. We also demonstrated that our labelling function was able to significantly reduce the initial label noise present in the dataset by up to a factor of three. Finally, we discuss different opportunities to design suitable labelling functions to build high-quality animal vocalizations with minimum expert annotation effort.     

Temporal Limitations on Social Learning of Novel Predators by Indian Mynahs, Acridotheres tristis

Antipredator vocalizations of social companions are important for facilitating long-term changes in the responses of prey to novel predator stimuli. However, dynamic variation in the time course of acoustic communication has important implications for learning of predator cues associated with auditory signals. While animals often experience acoustic signals simultaneously with predator cues, they may also at times experience signals and predator stimuli in succession. The ability to learn about stimuli that are perceived not only together, but also after, acoustic signals has the potential to expand the range of opportunities for learning about novel events. Earlier work in Indian mynahs ( Acridotheres tristis ) has revealed that subjects acquire a visual exploratory response to a novel avian mount after they have experienced it together with conspecific distress vocalizations, a call produced in response to seizure by a predator. The present study explored to what extent such learning occurred if the avian mount was experienced after, rather than simultaneously with, distress calls, such as might happen if call production is interrupted by prey death. Results showed that mynahs that experienced a novel avian mount simultaneously with the sound of distress calls exhibited a sustained exploratory response to the mount after training relative to before that was not apparent in birds that received distress calls and mount in succession. This finding suggests that vocal antipredator signals may only trigger learning of environmental stimuli with which they share some temporal overlap. Recipients may need to access complementary non-vocal cues from the prey victim to learn about predator stimuli that are perceived after vocal behaviour.     

The effect of body size and habitat on the evolution of alarm vocalizations in rodents

When confronted with a predator, many mammalian species emit vocalizations known as alarm calls. Vocal structure variation results from the interactive effects of different selective pressures and constraints affecting their production, transmission, and detection. Body size is an important morphological constraint influencing the lowest frequencies that an organism can produce. The acoustic environment influences signal degradation; low frequencies should be favoured in dense forests compared to more open habitats (i.e. the ‘acoustic adaptation hypothesis’). Such hypotheses have been mainly examined in birds, whereas the proximate and ultimate factors affecting vocalizations in nonprimate mammals have received less attention. In the present study, we investigated the relationships between the frequency of alarm calls, body mass, and habitat in 65 species of rodents. Although we found the expected negative relationship between call frequency and body mass, we found no significant differences in acoustic characteristics between closed and open‐habitat species. The results of the present study show that the acoustic frequencies of alarm calls can provide reliable information about the size of a sender in this taxonomic group, although they generally do not support the acoustic adaptation hypothesis.     

A comparison of individual distinctiveness in three vocalizations of the dwarf mongoose (Helogale parvula)

Individual specificity can be found in the vocalizations of many avian and mammalian species. However, it is often difficult to determine whether these vocal cues to identity rise from “unselected” individual differences in vocal morphology or whether they have been accentuated by selection for the purposes of advertising caller identity. By comparing the level of acoustic individuality of different vocalizations within the repertoire of a single species, it is possible to ascertain whether selection for individual recognition has modified the vocal cues to identity in particular contexts. We used discriminant function analyses to determine the level of accuracy with which calls could be classified to the correct individual caller, for three dwarf mongoose (Helogale parvula) vocalizations: contact, snake, and isolation calls. These calls were similar in acoustic structure but divergent in context and function. We found that all three call types showed individual specificity but levels varied with call type (increasing from snake to contact to isolation call). The individual distinctiveness of each call type appeared to be directly related to the degree of benefit that signalers were likely to accrue from advertising their identity within that call context. We conclude that dwarf mongoose signalers have undergone selection to facilitate vocal individual recognition, particularly in relation to the species’ isolation call.     

The function of nonlinear phenomena in meerkat alarm calls

Nonlinear vocal phenomena are a ubiquitous feature of human and non-human animal vocalizations. Although we understand how these complex acoustic intrusions are generated, it is not clear whether they function adaptively for the animals producing them. One explanation is that nonlinearities make calls more unpredictable, increasing behavioural responses and ultimately reducing the chances of habituation to these call types. Meerkats (Suricata suricatta) exhibit nonlinear subharmonics in their predator alarm calls. We specifically tested the ‘unpredictability hypothesis’ by playing back naturally occurring nonlinear and linear medium-urgency alarm call bouts. Results indicate that subjects responded more strongly and foraged less after hearing nonlinear alarm calls. We argue that these findings support the unpredictability hypothesis and suggest this is the first study in animals or humans to show that nonlinear vocal phenomena function adaptively.     

Habitat type and density influence vocal signal design in satin bowerbirds

1. This study provided a thorough test of the acoustic adaptation hypothesis using a within-species comparison of call structure involving a wide range of habitat types, an objective measure of habitat density and direct measures of habitat-related attenuation. 2. The structure of the bower advertisement call of the satin bowerbird was measured in 16 populations from throughout the species' range and related to the habitat type and density at each site. Transmission of white noise, pure tones and different bowerbird dialects was measured in five of six habitat types inhabited by satin bowerbirds. 3. Bowerbird advertisement call structure converged in similar habitats but diverged among different habitats; this pattern was apparent at both continent-wide and local geographical scales. Bowerbirds' call structures differed with changes in habitat density, consistent with the acoustic adaptation hypothesis. Lower frequencies and less frequency modulation were utilized in denser habitats such as rainforest and higher frequencies and more frequency modulation were used in the more open eucalypt-dominated habitats. 4. The white noise and pure tone transmission measurements indicated that different habitats varied in their sound transmission properties in a manner consistent with the observed variation in satin bowerbird vocalizations. 5. There was no effect of geographical proximity of recording locations, nor was there the predicted inverse relationship between frequency and body size. 6. These findings indicate that the transmission qualities of different habitats have had a major influence on variation in vocal phenotypes in this species. In addition, previously published molecular data for this species suggest that there is no effect of genetic relatedness on call similarity among satin bowerbird populations.     

Heterospecific Acoustic Interference: Effects on Calling in Oophaga pumilio

Call rate suppression is a common short-term solution for avoiding acoustic interference in animals. It has been widely documented between and within frog species, but the effects of non-anuran calling on frog vocalizations are less well known. Heterospecific acoustic interference on the calling of male Oophaga pumilio (formerly Dendrobates pumilio) was studied in a lowland, wet tropical forest in SE Nicaragua. Acoustic playback experiments were conducted to characterize the responses of O. pumilio males to interfering calls of cicadas, two species of crickets, and a sympatric dendrobatid frog, Phyllobates lugubris. Call rate, call bout duration, percent of time calling, dominant frequency, and latency to first-call were analyzed. Significant call rate suppression was observed during all stimulus playbacks, yet no significant differences were found in spontaneous call rates during pre- and postplayback trials. Dominant frequency significantly decreased after P. lugubris playback and first-call latency significantly decreased in response to both cicada and tree cricket playbacks. These results provide robust evidence that O. pumilio males can dynamically modify their calling pattern in unique ways, depending on the source of the heterospecific acoustic interference.     

Individuality in the vocalizations of infant and adult coppery titi monkeys (Plecturocebus cupreus)

As social animals, many primates use acoustic communication to maintain relationships. Vocal individuality has been documented in a diverse range of primate species and call types, many of which have presumably different functions. Auditory recognition of one's neighbors may confer a selective advantage if identifying conspecifics decreases the need to participate in costly territorial behaviors. Alternatively, vocal individuality may be nonadaptive and the result of a unique combination of genetics and environment. Pair-bonded primates, in particular, often participate in coordinated vocal duets that can be heard over long distances by neighboring conspecifics. In contrast to adult calls, infant vocalizations are short-range and used for intragroup communication. Here, we provide two separate but complementary analyses of vocal individuality in distinct call types of coppery titi monkeys (Plecturocebus cupreus) to test whether individuality occurs in call types from animals of different age classes with presumably different functions. We analyzed 600 trill vocalizations from 30 infants and 169 pulse-chirp duet vocalizations from 30 adult titi monkeys. We predicted that duet contributions would exhibit a higher degree of individuality than infant trills, given their assumed function for long-distance, intergroup communication. We estimated 7 features from infant trills and 16 features from spectrograms of adult pulse-chirps, then used discriminant function analysis with leave-one-out cross-validation to classify individuals. We correctly classified infants with 48% accuracy and adults with 83% accuracy. To further investigate variance in call features, we used a multivariate variance components model to estimate variance partitioning in features across two levels: within- and between-individuals. Between-individual variance was the most important source of variance for all features in adults, and three of four features in infants. We show that pulse-chirps of adult titi monkey duets are individually distinct, and infant trills are less individually distinct, which may be due to the different functions of the vocalizations.     

Ecological inferences about marine mammals from passive acoustic data

Monitoring on the basis of sound recordings, or passive acoustic monitoring, can complement or serve as an alternative to real-time visual or aural monitoring of marine mammals and other animals by human observers. Passive acoustic data can support the estimation of common, individual-level ecological metrics, such as presence, detection-weighted occupancy, abundance and density, population viability and structure, and behaviour. Passive acoustic data also can support estimation of some community-level metrics, such as species richness and composition. The feasibility of estimation and certainty of estimates is highly context dependent, and understanding the factors that affect the reliability of measurements is useful for those considering whether to use passive acoustic data. Here, we review basic concepts and methods of passive acoustic sampling in marine systems that often are applicable to marine mammal research and conservation. Our ultimate aim is to facilitate collaboration among ecologists, bioacousticians, and data analysts. Ecological applications of passive acoustics require one to make decisions about sampling design, which in turn requires consideration of sound propagation, sampling of signals, and data storage. One also must make decisions about signal detection and classification and evaluation of the performance of algorithms for these tasks. Investment in the research and development of systems that automate detection and classification, including machine learning, are increasing. Passive acoustic monitoring is more reliable for detection of species presence than for estimation of other species-level metrics. Use of passive acoustic monitoring to distinguish among individual animals remains difficult. However, information about detection probability, vocalisation or cue rate, and relations between vocalisations and the number and behaviour of animals increases the feasibility of estimating abundance or density. Most sensor deployments are fixed in space or are sporadic, making temporal turnover in species composition more tractable to estimate than spatial turnover. Collaborations between acousticians and ecologists are most likely to be successful and rewarding when all partners critically examine and share a fundamental understanding of the target variables, sampling process, and analytical methods.     

Social vocalizations of big brown bats vary with behavioral context

Bats are among the most gregarious and vocal mammals, with some species demonstrating a diverse repertoire of syllables under a variety of behavioral contexts. Despite extensive characterization of big brown bat (Eptesicus fuscus) biosonar signals, there have been no detailed studies of adult social vocalizations. We recorded and analyzed social vocalizations and associated behaviors of captive big brown bats under four behavioral contexts: low aggression, medium aggression, high aggression, and appeasement. Even limited to these contexts, big brown bats possess a rich repertoire of social vocalizations, with 18 distinct syllable types automatically classified using a spectrogram cross-correlation procedure. For each behavioral context, we describe vocalizations in terms of syllable acoustics, temporal emission patterns, and typical syllable sequences. Emotion-related acoustic cues are evident within the call structure by context-specific syllable types or variations in the temporal emission pattern. We designed a paradigm that could evoke aggressive vocalizations while monitoring heart rate as an objective measure of internal physiological state. Changes in the magnitude and duration of elevated heart rate scaled to the level of evoked aggression, confirming the behavioral state classifications assessed by vocalizations and behavioral displays. These results reveal a complex acoustic communication system among big brown bats in which acoustic cues and call structure signal the emotional state of a caller.     

Near-real-time acoustic monitoring of beaked whales and other cetaceans using a Seaglider™

In most areas, estimating the presence and distribution of cryptic marine mammal species, such as beaked whales, is extremely difficult using traditional observational techniques such as ship-based visual line transect surveys. Because acoustic methods permit detection of animals underwater, at night, and in poor weather conditions, passive acoustic observation has been used increasingly often over the last decade to study marine mammal distribution, abundance, and movements, as well as for mitigation of potentially harmful anthropogenic effects. However, there is demand for new, cost-effective tools that allow scientists to monitor areas of interest autonomously with high temporal and spatial resolution in near-real time. Here we describe an autonomous underwater vehicle--a glider--equipped with an acoustic sensor and onboard data processing capabilities to passively scan an area for marine mammals in near-real time. The glider was tested extensively off the west coast of the Island of Hawai'i, USA. The instrument covered approximately 390 km during three weeks at sea and collected a total of 194 h of acoustic data. Detections of beaked whales were successfully reported to shore in near-real time. Manual analysis of the recorded data revealed a high number of vocalizations of delphinids and sperm whales. Furthermore, the glider collected vocalizations of unknown origin very similar to those made by known species of beaked whales. The instrument developed here can be used to cost-effectively screen areas of interest for marine mammals for several months at a time. The near-real-time detection and reporting capabilities of the glider can help to protect marine mammals during potentially harmful anthropogenic activities such as seismic exploration for sub-sea fossil fuels or naval sonar exercises. Furthermore, the glider is capable of under-ice operation, allowing investigation of otherwise inaccessible polar environments that are critical habitats for many endangered marine mammal species.     

The use of Vocalizations of the Sambirano Mouse Lemur (<Emphasis Type="Italic">Microcebus sambiranensis</Emphasis>) in an Acoustic Survey of Habitat Preference

Primate vocalizations convey a variety of information to conspecifics. The acoustic traits of these vocalizations are an effective vocal fingerprint to discriminate between sibling species for taxonomic diagnosis. However, the vocal behavior of nocturnal primates has been poorly studied and there are few studies of their vocal repertoires. We compiled a vocal repertoire for the Endangered Sambirano mouse lemur, Microcebus sambiranensis, an unstudied nocturnal primate of northwestern Madagascar, and compared the acoustic properties of one of their call types to those of M. murinus and M. rufus. We recorded vocalizations from radio-collared individuals using handheld recorders over 3 months. We also conducted an acoustic survey to measure the vocal activity of M. sambiranensis in four forest habitat types at the study site. We identified and classified five vocalization types in M. sambiranensis. The vocal repertoires of the three Microcebus species contain very similar call types but have different acoustic properties, with one loud call type, the whistle, having significantly different acoustic properties between species. Our acoustic survey detected more calls of M. sambiranensis in secondary forest, riparian forest, and forest edge habitats, suggesting that individuals may prefer these habitat types over primary forest. Our results suggest interspecific differences in the vocal repertoire of mouse lemurs, and that these differences can be used to investigate habitat preference via acoustic surveys.     

Spectral call features provide information about the aggression level of greater mouse-eared bats (Myotis myotis) during agonistic interactions

Bats rely heavily on acoustic signals in order to communicate with each other in a variety of social contexts. Among those, agonistic interactions and accompanying vocalizations have received comparatively little study. Here, we studied the communicational behaviour between male greater mouse-eared bats (Myotis myotis) during agonistic encounters. Two randomly paired adult males were placed in a box that allowed us to record video and sound synchronously. We describe their vocal repertoire and compare the acoustic structure of vocalizations between two aggression levels, which we quantified via the bats’ behaviour. By inspecting thirty, one-minute long encounters, we identified a rich variety of social calls that can be described as two basic call types: echolocation-like, low-frequency sweeps and long, broadband squawks. Squawks, the most common vocalization, were often noisy, i.e. exhibited a chaotic spectral structure. We further provide evidence for individual signatures and the presence of nonlinear phenomena in this species’ vocal repertoire. As the usage and acoustic structure of vocalizations is known to encode the internal state of the caller, we had predicted that the spectral structure of squawks would be affected by the caller’s aggression level. Confirming our hypothesis, we found that increased aggression positively correlated with an increase in call frequency and tonality. We hypothesize that the extreme spectral variability between and within squawks can be explained by small fluctuations in vocal control parameters (e.g. subglottal pressure) that are caused by the elevated arousal, which is in turn influenced by the aggression level.     

Perceptual salience of acoustic differences between conspecific and allospecific vocalizations in African collared-doves

In speciation events, species-distinct vocal signals can diverge acoustically in many ways. Signal receivers have to be able to distinguish conspecific from allospecific vocalizations, and the perceptual salience of acoustic features is therefore expected to be an important factor in the evolution of such vocalizations. We tested how dissimilar the species-identifying perch-coos of 12 closely related turtle-dove species (genus Streptopelia) are, as perceived by one of its members, S. roseogrisea. With operant, psychoacoustic methods we trained six doves to respond only to their conspecific coo. Responses to the perch-coos of the 12 other dove species were used as a measure of their perceptual similarity to conspecific perch-coos. Turtle-doves differentiated between the allospecific coos: some were perceived as more similar to their own species' coo than others. With multiple regression analysis we identified three acoustic features that correlated with these differences in perceptual similarity: coo duration, minimum frequency and Wiener entropy. In contrast to findings in other bird species, duration was by far the most important feature in the discrimination between conspecific and allospecific vocalizations for S. roseogrisea. The results suggest that this is due not only to the coos of the various species differing in duration but also to a comparatively high perceptibility of the differences in duration. Copyright 2003 Published by Elsevier Science Ltd on behalf of The Association for the Study of Animal Behaviour.      

Structural Classification of Wild Boar (Sus scrofa) Vocalizations

Determining whether a species' vocal communication system is graded or discrete requires definition of its vocal repertoire. In this context, research on domestic pig (Sus scrofa domesticus) vocalizations, for example, has led to significant advances in our understanding of communicative functions. Despite their close relation to domestic pigs, little is known about wild boar (Sus scrofa) vocalizations. The few existing studies, conducted in the 1970s, relied on visual inspections of spectrograms to quantify acoustic parameters and lacked statistical analysis. Here, we use objective signal processing techniques and advanced statistical approaches to classify 616 calls recorded from semi‐free ranging animals. Based on four spectral and temporal acoustic parameters—quartile Q25, duration, spectral flux, and spectral flatness—extracted from a multivariate analysis, we refine and extend the conclusions drawn from previous work and present a statistically validated classification of the wild boar vocal repertoire into four call types: grunts, grunt‐squeals, squeals, and trumpets. While the majority of calls could be sorted into these categories using objective criteria, we also found evidence supporting a graded interpretation of some wild boar vocalizations as acoustically continuous, with the extremes representing discrete call types. The use of objective criteria based on modern techniques and statistics in respect to acoustic continuity advances our understanding of vocal variation. Integrating our findings with recent studies on domestic pig vocal behavior and emotions, we emphasize the importance of grunt‐squeals for acoustic approaches to animal welfare and underline the need of further research investigating the role of domestication on animal vocal communication.