Parameter estimation of the hyperbolic frequency-modulated bat calls using hyperbolic scale transform.

Echolocating bats are known to vary their waveforms at the phases of searching, approaching, and capturing the prey. It is meaningful to estimate the parameters of the calls for bat species identification and the technological improvements of the synthetic systems, such as radar and sonar. The type of bat calls is species-related, and many calls can be modeled as hyperbolic frequency- modulated (HFM) signals. To obtain the parameters of the HFM-modeled bat calls, a reversible integral transform, i.e., hyperbolic scale transform (HST), is proposed to transform a call into two-dimensional peaks in the "delay-scale" domain, based on which harmonic separation and parameter estimation are realized. Compared with the methods based on time-frequency analysis, the HST-based method does not need to extract the instantaneous frequency of the bat calls, only searching for peaks. The verification results show that the HST is suitable for analyzing the HFM-modeled bat calls containing multiple harmonics with a large energy difference, and the estimated parameters imply that the use of the waveforms from the searching phase to the capturing phase is beneficial to reduce the ranging bias, and the trends in parameters may be useful for bat species identification.

Enhancing the analysis of murine neonatal ultrasonic vocalizations: Development, evaluation, and application of different mathematical models.

Rodents employ a broad spectrum of ultrasonic vocalizations (USVs) for social communication. As these vocalizations offer valuable insights into affective states, social interactions, and developmental stages of animals, various deep learning approaches have aimed at automating both the quantitative (detection) and qualitative (classification) analysis of USVs. So far, no notable efforts have been made to determine the most suitable architecture. We present the first systematic evaluation of different types of neural networks for USV classification. We assessed various feedforward networks, including a custom-built, fully-connected network, a custom-built convolutional neural network, several residual neural networks, an EfficientNet, and a Vision Transformer. Our analysis concluded that convolutional networks with residual connections specifically adapted to USV data, are the most suitable architecture for analyzing USVs. Paired with a refined, entropy-based detection algorithm (achieving recall of 94.9 % and precision of 99.3 %), the best architecture (achieving 86.79 % accuracy) was integrated into a fully automated pipeline capable of analyzing extensive USV datasets with high reliability. In ongoing projects, our pipeline has proven to be a valuable tool in studying neonatal USVs. By comparing these distinct deep learning architectures side by side, we have established a solid foundation for future research.

Use of whistles for acoustic classification of delphinids (odontoceti: Delphinidae) in the Western South Atlantic Ocean.

This study focuses on the acoustic classification of delphinid species at the southern continental slope of Brazil. Recordings were collected between 2013 and 2015 using towed arrays and were processed using a classifier to identify the species in the recordings. Using Raven Pro 1.6 software (Cornell Laboratory of Ornithology, Ithaca, NY), we analyzed whistles for species identification. The random forest algorithm in R facilitates classification analysis based on acoustic parameters, including low, high, delta, center, beginning, and ending frequencies, and duration. Evaluation metrics, such as correct and incorrect classification percentages, global accuracy, balanced accuracy, and p-values, were employed. Receiver operating characteristic curves and area-under-the-curve (AUC) values demonstrated well-fitting models (AUC ≥ 0.7) for species definition. Duration and delta frequency emerged as crucial parameters for classification, as indicated by the decrease in mean accuracy. Multivariate dispersion plots visualized the proximity between acoustic and visual match data and exclusively acoustic encounter (EAE) data. The EAE results classified as Delphinus delphis (n = 6), Stenella frontalis (n = 3), and Stenella longirostris (n = 2) provide valuable insights into the presence of these species between approximately 23° and 34° S in Brazil. This study demonstrates the effectiveness of acousting classification in discriminating delphinids through whistle parameters.

Measuring context dependency in birdsong using artificial neural networks.

Context dependency is a key feature in sequential structures of human language, which requires reference between words far apart in the produced sequence. Assessing how long the past context has an effect on the current status provides crucial information to understand the mechanism for complex sequential behaviors. Birdsongs serve as a representative model for studying the context dependency in sequential signals produced by non-human animals, while previous reports were upper-bounded by methodological limitations. Here, we newly estimated the context dependency in birdsongs in a more scalable way using a modern neural-network-based language model whose accessible context length is sufficiently long. The detected context dependency was beyond the order of traditional Markovian models of birdsong, but was consistent with previous experimental investigations. We also studied the relation between the assumed/auto-detected vocabulary size of birdsong (i.e., fine- vs. coarse-grained syllable classifications) and the context dependency. It turned out that the larger vocabulary (or the more fine-grained classification) is assumed, the shorter context dependency is detected.

DetEdit: A graphical user interface for annotating and editing events detected in long-term acoustic monitoring data.

Passive acoustic monitoring has become an important data collection method, yielding massive datasets replete with biological, environmental and anthropogenic information. Automated signal detectors and classifiers are needed to identify events within these datasets, such as the presence of species-specific sounds or anthropogenic noise. These automated methods, however, are rarely a complete substitute for expert analyst review. The ability to visualize and annotate acoustic events efficiently can enhance scientific insights from large, previously intractable datasets. A MATLAB-based graphical user interface, called DetEdit, was developed to accelerate the editing and annotating of automated detections from extensive acoustic datasets. This tool is highly-configurable and multipurpose, with uses ranging from annotation and classification of individual signals or signal-clusters and evaluation of signal properties, to identification of false detections and false positive rate estimation. DetEdit allows users to step through acoustic events, displaying a range of signal features, including time series of received levels, long-term spectral averages, time intervals between detections, and scatter plots of peak frequency, RMS, and peak-to-peak received levels. Additionally, it displays either individual, or averaged sound pressure waveforms, and power spectra within each acoustic event. These views simultaneously provide analysts with signal-level detail and encounter-level context. DetEdit creates datasets of signal labels for further analyses, such as training classifiers and quantifying occurrence, abundances, or trends. Although designed for evaluating underwater-recorded odontocete echolocation click detections, DetEdit can be adapted to almost any stereotyped impulsive signal. Our software package complements available tools for the bioacoustic community and is provided open source at https://github.com/MarineBioAcousticsRC/DetEdit.

Comparison of methods for rhythm analysis of complex animals' acoustic signals.

Analyzing the rhythm of animals' acoustic signals is of interest to a growing number of researchers: evolutionary biologists want to disentangle how these structures evolved and what patterns can be found, and ecologists and conservation biologists aim to discriminate cryptic species on the basis of parameters of acoustic signals such as temporal structures. Temporal structures are also relevant for research on vocal production learning, a part of which is for the animal to learn a temporal structure. These structures, in other words, these rhythms, are the topic of this paper. How can they be investigated in a meaningful, comparable and universal way? Several approaches exist. Here we used five methods to compare their suitability and interpretability for different questions and datasets and test how they support the reproducibility of results and bypass biases. Three very different datasets with regards to recording situation, length and context were analyzed: two social vocalizations of Neotropical bats (multisyllabic, medium long isolation calls of Saccopteryx bilineata, and monosyllabic, very short isolation calls of Carollia perspicillata) and click trains of sperm whales, Physeter macrocephalus. Techniques to be compared included Fourier analysis with a newly developed goodness-of-fit value, a generate-and-test approach where data was overlaid with varying artificial beats, and the analysis of inter-onset-intervals and calculations of a normalized Pairwise Variability Index (nPVI). We discuss the advantages and disadvantages of the methods and we also show suggestions on how to best visualize rhythm analysis results. Furthermore, we developed a decision tree that will enable researchers to select a suitable and comparable method on the basis of their data.

Finding, visualizing, and quantifying latent structure across diverse animal vocal repertoires.

Animals produce vocalizations that range in complexity from a single repeated call to hundreds of unique vocal elements patterned in sequences unfolding over hours. Characterizing complex vocalizations can require considerable effort and a deep intuition about each species' vocal behavior. Even with a great deal of experience, human characterizations of animal communication can be affected by human perceptual biases. We present a set of computational methods for projecting animal vocalizations into low dimensional latent representational spaces that are directly learned from the spectrograms of vocal signals. We apply these methods to diverse datasets from over 20 species, including humans, bats, songbirds, mice, cetaceans, and nonhuman primates. Latent projections uncover complex features of data in visually intuitive and quantifiable ways, enabling high-powered comparative analyses of vocal acoustics. We introduce methods for analyzing vocalizations as both discrete sequences and as continuous latent variables. Each method can be used to disentangle complex spectro-temporal structure and observe long-timescale organization in communication.

An automated approach to the quantitation of vocalizations and vocal learning in the songbird.

Studies of learning mechanisms critically depend on the ability to accurately assess learning outcomes. This assessment can be impeded by the often complex, multidimensional nature of behavior. We present a novel, automated approach to evaluating imitative learning. Conceptually, our approach estimates how much of the content present in a reference behavior is absent from the learned behavior. We validate our approach through examination of songbird vocalizations, complex learned behaviors the study of which has provided many insights into sensory-motor learning in general and vocal learning in particular. Historically, learning has been holistically assessed by human inspection or through comparison of specific song features selected by experimenters (e.g. fundamental frequency, spectral entropy). In contrast, our approach uses statistical models to broadly capture the structure of each song, and then estimates the divergence between the two models. We show that our measure of song learning (the Kullback-Leibler divergence between two distributions corresponding to specific song data, or, Song DKL) is well correlated with human evaluation of song learning. We then expand the analysis beyond learning and show that Song DKL also detects the typical song deterioration that occurs following deafening. Finally, we illustrate how this measure can be extended to quantify differences in other complex behaviors such as human speech and handwriting. This approach potentially provides a framework for assessing learning across a broad range of behaviors like song that can be described as a set of discrete and repeated motor actions.

Deep convolutional network for animal sound classification and source attribution using dual audio recordings.

This paper introduces an end-to-end feedforward convolutional neural network that is able to reliably classify the source and type of animal calls in a noisy environment using two streams of audio data after being trained on a dataset of modest size and imperfect labels. The data consists of audio recordings from captive marmoset monkeys housed in pairs, with several other cages nearby. The network in this paper can classify both the call type and which animal made it with a single pass through a single network using raw spectrogram images as input. The network vastly increases data analysis capacity for researchers interested in studying marmoset vocalizations, and allows data collection in the home cage, in group housed animals.

Species Boundaries within Morphologically Cryptic Galagos: Evidence from Acoustic and Genetic Data.

Describing primate biodiversity is one of the main goals in primatology. Species are the fundamental unit of study in phylogeny, behaviour, ecology and conservation. Identifying species boundaries is particularly challenging for nocturnal taxa where only subtle morphological variation is present. Traditionally, vocal signals have been used to identify species within nocturnal primates: species-specific signals often play a critical role in mate recognition, and they can restrict gene flow with other species. However, little research has been conducted to test whether different "acoustic forms" also represent genetically distinct species. Here, we investigate species boundaries between two putative highly cryptic species of Eastern dwarf galagos (Paragalago cocosand P. zanzibaricus). We combined vocal and genetic data: molecular data included the complete mitochondrial cytochrome b gene (1,140 bp) for 50 samples across 11 localities in Kenya and Tanzania, while vocal data comprised 221 vocalisations recorded across 8 localities. Acoustic analyses showed a high level of correct assignation to the putative species (approx. 90%), while genetic analyses identified two separate clades at the mitochondrial level. We conclude that P. cocos and P. zanzibaricus represent two valid cryptic species that probably underwent speciation in the Late Pliocene while fragmented in isolated populations in the eastern forests.

Evolutionarily conserved coding properties favour the neuronal representation of heterospecific signals of a sympatric katydid species.

To function as a mechanism in premating isolation, the divergent and species-specific calling songs of acoustic insects must be reliably processed by the afferent auditory pathway of receivers. Here, we analysed the responses of interneurons in a katydid species that uses long-lasting acoustic trills and compared these with previously reported data for homologous interneurons of a sympatric species that uses short chirps as acoustic signals. Some interneurons of the trilling species respond exclusively to the heterospecific chirp due to selective, low-frequency tuning and "novelty detection". These properties have been considered as evolutionary adaptations in the sensory system of the chirper, which allow it to detect signals effectively during the simultaneous calling of the sympatric sibling species. We propose that these two mechanisms, shared by the interneurons of both species, did not evolve in the chirper to guarantee its ability to detect the chirp under masking conditions. Instead we suggest that chirpers evolved an additional, 2-kHz component in their song and exploited pre-existing neuronal properties for detecting their song under masking noise. The failure of some interneurons to respond to the conspecific song in trillers does not prevent intraspecific communication, as other interneurons respond to the trill.

Automated classification of dolphin echolocation click types from the Gulf of Mexico.

Delphinids produce large numbers of short duration, broadband echolocation clicks which may be useful for species classification in passive acoustic monitoring efforts. A challenge in echolocation click classification is to overcome the many sources of variability to recognize underlying patterns across many detections. An automated unsupervised network-based classification method was developed to simulate the approach a human analyst uses when categorizing click types: Clusters of similar clicks were identified by incorporating multiple click characteristics (spectral shape and inter-click interval distributions) to distinguish within-type from between-type variation, and identify distinct, persistent click types. Once click types were established, an algorithm for classifying novel detections using existing clusters was tested. The automated classification method was applied to a dataset of 52 million clicks detected across five monitoring sites over two years in the Gulf of Mexico (GOM). Seven distinct click types were identified, one of which is known to be associated with an acoustically identifiable delphinid (Risso's dolphin) and six of which are not yet identified. All types occurred at multiple monitoring locations, but the relative occurrence of types varied, particularly between continental shelf and slope locations. Automatically-identified click types from autonomous seafloor recorders without verifiable species identification were compared with clicks detected on sea-surface towed hydrophone arrays in the presence of visually identified delphinid species. These comparisons suggest potential species identities for the animals producing some echolocation click types. The network-based classification method presented here is effective for rapid, unsupervised delphinid click classification across large datasets in which the click types may not be known a priori.

Vocal repertoire of free-ranging adult golden snub-nosed monkeys (Rhinopithecus roxellana).

Vocal signaling represents a primary mode of communication for most nonhuman primates. A quantitative description of the vocal repertoire is a critical step in in-depth studies of the vocal communication of particular species, and provides the foundation for comparative studies to investigate the selective pressures in the evolution of vocal communication systems. The present study was the first attempt to establish the vocal repertoire of free-ranging adult golden snub-nosed monkeys (Rhinopithecus roxellana) based on quantitative methods. During 8 months in Shennongjia National Park, China, we digitally recorded the vocalizations of adult individuals from a provisioned, free-ranging group of R. roxellana across a variety of social-ecological contexts. We identified 18 call types, which were easily distinguishable by ear, visual inspection of spectrograms, and quantitative analysis of acoustic parameters measured from recording samples. We found a great sexual asymmetry in the vocal repertoire size (females produced many more call types than males), likely due to the sex differences in body size and social role. We found a variety of call types that occurred during various forms of agonistic and affiliative interactions at close range. We made inference about the functions of particular call types based on the contexts in which they were produced. Studies on the vocal communication in R. roxellana are particularly valuable since they provide a case about how nonhuman primates, inhabiting forest habitats and forming complex social systems, use their vocalizations to interact with their social and ecological environments.

Local compressed convex spectral embedding for bird species identification.

This paper proposes a multi-layer alternating sparse-dense framework for bird species identification. The framework takes audio recordings of bird vocalizations and produces compressed convex spectral embeddings (CCSE). Temporal and frequency modulations in bird vocalizations are ensnared by concatenating frames of the spectrogram, resulting in a high dimensional and highly sparse super-frame-based representation. Random projections are then used to compress these super-frames. Class-specific archetypal analysis is employed on the compressed super-frames for acoustic modeling, obtaining the convex-sparse CCSE representation. This representation efficiently captures species-specific discriminative information. However, many bird species exhibit high intra-species variations in their vocalizations, making it hard to appropriately model the whole repertoire of vocalizations using only one dictionary of archetypes. To overcome this, each class is clustered using Gaussian mixture models (GMM), and for each cluster, one dictionary of archetypes is learned. To calculate CCSE for any compressed super-frame, one dictionary from each class is chosen using the responsibilities of individual GMM components. The CCSE obtained using this GMM-archetypal analysis framework is referred to as local CCSE. Experimental results corroborate that local CCSE either outperforms or exhibits comparable performances to existing methods including support vector machine powered by dynamic kernels and deep neural networks.

Species-level classification of beaked whale echolocation signals detected in the northern Gulf of Mexico.

This study presents and evaluates several methods for automated species-level classification of echolocation clicks from three beaked whale species recorded in the northern Gulf of Mexico. The species included are Cuvier's and Gervais' beaked whales, as well as an unknown species denoted Beaked Whale Gulf. An optimal feature set for discriminating the three click types while also separating detected clicks from unidentified delphinids was determined using supervised step-wise discriminant analysis. Linear and quadratic discriminant analyses both achieved error rates below 1% with three features, determined by tenfold cross validation. The waveform fractal dimension was found to be a highly ranked feature among standard spectral and temporal parameters. The top-ranking features were Higuchi's fractal dimension, spectral centroid, Katz's fractal dimension, and -10 dB duration. Six clustering routines, including four popular network-based algorithms, were also evaluated as unsupervised classification methods using the selected feature set. False positive rates of 0.001 and 0.024 were achieved by Chinese Whispers and spectral clustering, respectively, across 200 randomized trials. However, Chinese Whispers clustering yielded larger false negative rates. Spectral clustering was further tested on clicks from encounters of beaked, sperm, and pilot whales in the Tongue of the Ocean, Bahamas.

Characteristics of vocalisations recorded from free-ranging Shepherd's beaked whales, Tasmacetus shepherdi.

Beaked whales (family Ziphiidae) are among the least studied of all the large mammals. This is especially true of Shepherd's beaked whale (Tasmacetus shepherdi), which until recently had been very rarely sighted alive, with nothing known about the species' acoustic behaviour. Vocalisations of Shepherd's beaked whales were recorded using a hydrophone array on two separate days during marine mammal surveys of the Otago submarine canyons in New Zealand. After carefully screening the recordings, two distinct call types were found; broadband echolocation clicks, and burst pulses. Broadband echolocation clicks (n = 476) had a median inter-click-interval (ICI) of 0.46 s and median peak frequency of 19.2 kHz. The burst pulses (n = 33) had a median peak frequency of constituent clicks (n = 1741) of 14.7 kHz, and median ICI of 11 ms. These results should be interpreted with caution due to the limited bandwidth used to record the signals. To the authors' knowledge, this study presents the first analysis of the characteristics of Shepherd's beaked whale sounds. It will help with identification of the species in passive acoustic monitoring records, and future efforts to further analyse this species' vocalisations.

Resource-Efficient Pet Dog Sound Events Classification Using LSTM-FCN Based on Time-Series Data.

The use of IoT (Internet of Things) technology for the management of pet dogs left alone at home is increasing. This includes tasks such as automatic feeding, operation of play equipment, and location detection. Classification of the vocalizations of pet dogs using information from a sound sensor is an important method to analyze the behavior or emotions of dogs that are left alone. These sounds should be acquired by attaching the IoT sound sensor to the dog, and then classifying the sound events (e.g., barking, growling, howling, and whining). However, sound sensors tend to transmit large amounts of data and consume considerable amounts of power, which presents issues in the case of resource-constrained IoT sensor devices. In this paper, we propose a way to classify pet dog sound events and improve resource efficiency without significant degradation of accuracy. To achieve this, we only acquire the intensity data of sounds by using a relatively resource-efficient noise sensor. This presents issues as well, since it is difficult to achieve sufficient classification accuracy using only intensity data due to the loss of information from the sound events. To address this problem and avoid significant degradation of classification accuracy, we apply long short-term memory-fully convolutional network (LSTM-FCN), which is a deep learning method, to analyze time-series data, and exploit bicubic interpolation. Based on experimental results, the proposed method based on noise sensors (i.e., Shapelet and LSTM-FCN for time-series) was found to improve energy efficiency by 10 times without significant degradation of accuracy compared to typical methods based on sound sensors (i.e., mel-frequency cepstrum coefficient (MFCC), spectrogram, and mel-spectrum for feature extraction, and support vector machine (SVM) and k-nearest neighbor (K-NN) for classification).

Ontogeny of individual and litter identity signaling in grunts of piglets.

Many studies have shown that animal vocalizations can signal individual identity and group/family membership. However, much less is known about the ontogeny of identity information-when and how this individual/group distinctiveness in vocalizations arises and how it changes during the animal's life. Recent findings suggest that even species that were thought to have limited vocal plasticity could adjust their calls to sound more similar to each other within a group. It has already been shown that sows can acoustically distinguish their own offspring from alien piglets and that litters differ in their calls. Surprisingly, individual identity in piglet calls has not been reported yet. In this paper, this gap is filled, and it is shown that there is information about piglet identity. Information about litter identity is confirmed as well. Individual identity increased with age, but litter vocal identity did not increase with age. The results were robust as a similar pattern was apparent in two situations differing in arousal: isolation and back-test. This paper argues that, in piglets, increased individual discrimination results from the rapid growth of piglets, which is likely to be associated with growth and diversification of the vocal tract rather than from social effects and vocal plasticity.

Active learning for bird sound classification via a kernel-based extreme learning machine.

In recent years, research fields, including ecology, bioacoustics, signal processing, and machine learning, have made bird sound recognition a part of their focus. This has led to significant advancements within the field of ornithology, such as improved understanding of evolution, local biodiversity, mating rituals, and even the implications and realities associated to climate change. The volume of unlabeled bird sound data is now overwhelming, and comparatively little exploration is being made into methods for how best to handle them. In this study, two active learning (AL) methods are proposed, sparse-instance-based active learning (SI-AL), and least-confidence-score-based active learning (LCS-AL), both effectively reducing the need for expert human annotation. To both of these AL paradigms, a kernel-based extreme learning machine (KELM) is then integrated, and a comparison is made to the conventional support vector machine (SVM). Experimental results demonstrate that, when the classifier capacity is improved from an unweighted average recall of 60%-80%, KELM can outperform SVM even when a limited proportion of human annotations are used from the pool of data in both cases of SI-AL (minimum 34.5% vs minimum 59.0%) and LCS-AL (minimum 17.3% vs minimum 28.4%).

Allometric trends reveal distinct evolutionary trajectories for avian communication.

Acoustic signal production is affected by allometric relationships, by which the larger the animal, the lower its call frequency. In this paper, three evolutionary acoustic hypotheses were tested: the Signal-to-Noise Ratio Hypothesis (SNRH), in which evolution maximizes call ranges by increasing the signal-to-noise ratio; the Stimulus Threshold Hypothesis (STH), in which evolution maximizes the range of a specific signal threshold; and the Body Size Hypothesis (BSH), in which the emission of long wavelengths is enabled by body size. Three spectral metrics were measured, Dominant Frequency (FDOM), Minimum Fundamental Frequencies (FFMIN), and Maximum Fundamental Frequencies (FFMAX) of Neotropical Parrots, New World Doves, Woodcreepers, Tinamous, and Thrushes. A Ranged Major Axis (RMA) regression showed that body mass is significantly correlated with all of the spectral parameters in Parrots, Doves, and Woodcreepers, but only with the fundamental frequencies of Tinamous. The FDOM of Parrots corroborated the SNRH. The FFMIN of Woodcreepers and Tinamous corroborated the SNRH and BSH. The FFMAX of Parrots corroborated the STH and BSH. Those acoustic hypotheses could shed light on the evolutionary processes involved in avian communication, although results indicate that these depend on the taxa and spectral parameters considered.