Search Results (140)

This study highlights the potential of aquariums as research platforms for bioacoustic research. Aquariums provide access to a wide variety of fish species, offering unique opportunities to characterize their acoustic features in controlled settings. In particular, we present a preliminary description of the acoustic characteristics of Myripristis jacobus, a soniferous species in the Holocentridae family, within a controlled environment at a zoological facility in the Canary Islands, Spain. Using two HydroMoth 1.0 hydrophones, we recorded vocalizations of the blackbar soldierfish in a glass tank, revealing a pulsed sound type with a peak frequency around 355 Hz (DS 64), offering a more precise characterization than previously available. The vocalizations exhibit two distinct patterns: short sequences with long pulse intervals and fast pulse trains with short inter-pulse intervals. Despite some limitations, this experimental setup highlights the efficacy of cost-effective methodologies in public aquariums for initial bioacoustic research. These findings contribute to the early stages of acoustic characterization of coastal fishes in the western central Atlantic, emphasizing the value of passive acoustic monitoring for ecological assessments and conservation efforts. Moreover, this study opens new avenues for considering the acoustic environment as a crucial factor in the welfare of captive fish, an aspect that has largely been overlooked in aquarium management. Full article

Urban natural parks represent a remarkable concept that evokes the coexistence of human habitation with a wild environment, and the associated interactions between human and natural territories. In this context, urban noise infringes upon the natural soundscape, leading to various consequences for both realms. This study seeks to characterize the impact of anthropic noise levels on biodiversity in the urban natural Văcărești Park (Bucharest, Romania), utilizing on-site measurements and software simulation techniques. The study seeks to develop a method for evaluating integrative strategies to mitigate the impact of traffic noise on wildlife in an urban wild park, without addressing the specific effects of noise on the perception and communication of individual species. By calibrating field measurements with laboratory results, a more reliable data set will be used to identify areas where the biophonic environment is impacted by anthropogenic noise. Since human-generated noise in an urban natural park predominantly originates from road traffic and industrial sites, managing traffic noise and its propagation pathways could substantially improve the park’s soundscape. Additionally, this study will apply software simulations for noise reduction strategies, such as vegetation planting and earthen embankments, to obtain suitable solutions and propose plausible and effective actions to authorities for improving the biophonic environment. This research could also serve as the basis for long-term monitoring, allowing for the assessment of the evolution and impact of implemented measures over time. Full article

Whale sound is a typical transient signal. The escalating demands of ecological research and marine conservation necessitate advanced technologies for the automatic detection and classification of underwater acoustic signals. Traditional energy detection methods, which focus primarily on amplitude, often perform poorly in the non-Gaussian noise conditions typical of oceanic environments. This study introduces a classified-before-detect approach that overcomes the limitations of amplitude-focused techniques. We also address the challenges posed by deep learning models, such as high data labeling costs and extensive computational requirements. By extracting shape statistical features from audio and using the XGBoost classifier, our method not only outperforms the traditional convolutional neural network (CNN) method in accuracy but also reduces the dependence on labeled data, thus improving the detection efficiency. The integration of these features significantly enhances model performance, promoting the broader application of marine acoustic remote sensing technologies. This research contributes to the advancement of marine bioacoustic monitoring, offering a reliable, rapid, and training-efficient method suitable for practical deployment. Full article

In recent years, several automated and noninvasive methods for wildlife monitoring, such as passive acoustic monitoring (PAM), have emerged. PAM consists of the use of acoustic sensors followed by sound interpretation to obtain ecological information about certain species. One challenge associated with PAM is the generation of a significant amount of data, which often requires the use of machine learning tools for automated recognition. Here, we couple PAM with BirdNET, a free-to-use sound algorithm to assess, for the first time, the precision of BirdNET in predicting three tropical songbirds and to describe their patterns of vocal activity over a year in the Brazilian Pantanal. The precision of the BirdNET method was high for all three species (ranging from 72 to 84%). We were able to describe the vocal activity patterns of two of the species, the Buff-breasted Wren (Cantorchilus leucotis) and Thrush-like Wren (Campylorhynchus turdinus). Both species presented very similar vocal activity patterns during the day, with a maximum around sunrise, and throughout the year, with peak vocal activity occurring between April and June, when food availability for insectivorous species may be high. Further research should improve our knowledge regarding the ability of coupling PAM with BirdNET for monitoring a wider range of tropical species. Full article

As part of the ecosystem, the western black-crested gibbon (Nomascus concolor) is important for ecological sustainability. Calls are an important means of communication for gibbons, so accurately recognizing and categorizing gibbon calls is important for their population monitoring and conservation. Since a large amount of sound data will be generated in the process of acoustic monitoring, it will take a lot of time to recognize the gibbon calls manually, so this paper proposes a western black-crested gibbon call recognition network based on SA_DenseNet-LSTM-Attention. First, to address the lack of datasets, this paper explores 10 different data extension methods to process all the datasets, and then converts all the sound data into Mel spectrograms for model input. After the test, it is concluded that WaveGAN audio data augmentation method obtains the highest accuracy in improving the classification accuracy of all models in the paper. Then, the method of fusion of DenseNet-extracted features and LSTM-extracted temporal features using PCA principal component analysis is proposed to address the problem of the low accuracy of call recognition, and finally, the SA_DenseNet-LSTM-Attention western black-crested gibbon call recognition network proposed in this paper is used for recognition training. In order to verify the effectiveness of the feature fusion method proposed in this paper, we classified 13 different types of sounds and compared several different networks, and finally, the accuracy of the VGG16 model improved by 2.0%, the accuracy of the Xception model improved by 1.8%, the accuracy of the MobileNet model improved by 2.5%, and the accuracy of the DenseNet network model improved by 2.3%. Compared to other classical chirp recognition networks, our proposed network obtained the highest accuracy of 98.2%, and the convergence of our model is better than all the compared models. Our experiments have demonstrated that the deep learning-based call recognition method can provide better technical support for monitoring western black-crested gibbon populations. Full article

The western black-crested gibbon (Nomascus concolor) is a rare and endangered primate that inhabits southern China and northern Vietnam, and has become a key conservation target due to its distinctive call and highly endangered status, making its identification and monitoring particularly urgent. Identifying calls of the western black-crested gibbon using passive acoustic monitoring data is a crucial method for studying and analyzing these gibbons; however, traditional call recognition models often overlook the temporal information in audio features and fail to adapt to channel-feature weights. To address these issues, we propose an innovative deep learning model, VBSNet, designed to recognize and classify a variety of biological calls, including those of endangered western black-crested gibbons and certain bird species. The model incorporates the image feature extraction capability of the VGG16 convolutional network, the sequence modeling capability of bi-directional LSTM, and the feature selection capability of the SE attention module, realizing the multimodal fusion of image, sequence and attention information. In the constructed dataset, the VBSNet model achieved the best performance in the evaluation metrics of accuracy, precision, recall, and F1-score, realizing an accuracy of 98.35%, demonstrating high accuracy and generalization ability. This study provides an effective deep learning method in the field of automated bioacoustic monitoring, which is of great theoretical and practical significance for supporting wildlife conservation and maintaining biodiversity. Full article

The acoustic communication system (ACS) in bark beetles has been studied mainly in species of the genera Dendroctonus, Ips and Polygraphus. Specifically, ACS of the roundheaded pine beetle, Dendroctonus adjunctus, has been little studied. In this study, we described the stridulatory apparatus of this beetle using optical and scanning electron microscopy and recorded the call types produced by males in three behavioral contexts: stress, female–male–, and male–male interactions. From the spectrograms and waveforms, call types, as well as temporal (tooth strike, tooth strike rate, and intertooth strike interval) and spectral features (minimum, maximum and dominant frequency), were determined. Males have a functional elytro–tergal stridulatory apparatus—females do not—consisting of a file for the pars stridens and two lobes for the plectrum. Most of spectro–temporal features were statistically different between single– and multi–noted calls and across the three behavioral contexts. In the male–male interaction, a new type of call named “withdrawal” was produced by the male withdrawing or fleeing. Our results suggest that the spectro–temporal features of single– and multiple–noted calls in the three behavioral conditions are specific and different from each other. Yet, the combination of single and multiple calls determines an overall calling pattern characteristic of the tested behaviors and, therefore, is species–specific. Full article

Insect-eating bats play a crucial role in agriculture and public health by suppressing populations of agricultural pests and disease vectors. These ecosystem services promoted by insect-eating bats are essential in a world that seeks sustainability in agricultural production and the management of urban areas. Despite Brazil’s status as one of the largest agricultural producers globally, research using insect-eating bats for pest control is lacking. This review underscores the importance of filling this knowledge gap and provides guidelines for future research. Bats exhibit diverse feeding habits and consume significant quantities of insects, including agricultural pests. While studies in the USA and Europe have highlighted insect-eating bats’ role in reducing agricultural losses, research in Brazil is limited. Challenges include the need for more advanced diet analysis techniques, such as DNA metabarcoding, and understanding bat habitat use in agricultural and urban landscapes. Research on natural and artificial roosts’ effectiveness and population dynamics is also essential. Integrating bat conservation into agricultural sustainability requires investment in technological methods, valuation of ecosystem services, population monitoring, habitat use studies and environmental education. Financial incentives and collaboration between sectors are crucial for advancing research and implementing bat-friendly practices in agriculture, ultimately enhancing biodiversity conservation and production sustainability in Brazil. Full article

Bioacoustic event detection is a demanding endeavor involving recognizing and classifying the sounds animals make in their natural habitats. Traditional supervised learning requires a large amount of labeled data, which are hard to come by in bioacoustics. This paper presents a few-shot learning (FSL) method incorporating transductive inference and data augmentation to address the issues of too few labeled events and small volumes of recordings. Here, transductive inference iteratively alters class prototypes and feature extractors to seize essential patterns, whereas data augmentation applies SpecAugment on Mel spectrogram features to augment training data. The proposed approach is evaluated by using the Detecting and Classifying Acoustic Scenes and Events (DCASE) 2022 and 2021 datasets. Extensive experimental results demonstrate that all components of the proposed method achieve significant F-score improvements of 27% and 10%, for the DCASE-2022 and DCASE-2021 datasets, respectively, compared to recent advanced approaches. Moreover, our method is helpful in FSL tasks because it effectively adapts to sounds from various animal species, recordings, and durations. Full article

Hearing loss can result from impairments in structures that support endocochlear potential, as they play a crucial role in the transduction and transmission of auditory waves. This aspect has been the subject of several studies to date. In our review, the role of ion transport channels and pumps involved in hearing function has been highlighted, emphasizing how important the Kir4.1 channel is in maintaining the endocochlear potential. The Kir4.1 channel, a member of the inwardly rectifying potassium channel (Kir) family, plays a key role in the regulation of cell electrical activity and potassium ion homeostasis. The cochlear expression of these channels is at the level of the intermediate cells of the vascular stria, in the root cells of the outer sulcus, and in the glial cells of the spiral ganglion. In development, its expression demonstrates its involvement in the progression of pathologies related to potassium channel dysfunction, and its activation in the stria vascularis is directly related to the generation of endocochlear potential. Kir4.1 is fundamental in stabilizing the resting membrane potential of cells and modulating their excitability, as it facilitates a greater influx of potassium into cells compared to efflux when the membrane potential is negative. Mutations in the K⁺ channel gene KCNJ10 (Kir4.1) have been associated with several disorders, with the most significant studies on EAST/SeSAME syndrome and Pendred syndrome. Recent research has explored the metabolic importance of potassium channel changes associated with stria vascularis degeneration in the progression of age-related hearing loss. Furthermore, in ototoxicity studies, the Kir4.1 channel has been shown to have the ability to compensate for the deficiency of other K⁺ channels, as it maintains the cochlear homeostasis by correcting the imbalanced K⁺ concentration. Full article

Passerines are the most successfully diversified bird order (around 60% of all avian species). They have developed complicated songs to defend their territories and to attract females for mating that can evolve quickly due to cultural transmission. Complex singing as well as plumage coloration of male birds are honest signals for potential partners and provide information about the males’ quality. To function as honest signals, both traits must be costly for the males. Of course, not all passerine species are equally clever or beautiful. Even within a single family of 50 to 70 species, relevant traits may vary considerably. Tits and chickadees (Paridae) comprise species of similar size, varying a lot in coloration and plumage pattern. The territorial songs are relatively short and simple. We investigated the relationship between song complexity and plumage coloration, taking phylogenetic relationships into account. We studied 55 out of the 64 species with 1084 song recordings retrieved from an online database. In the best model, besides colorfulness, body size had a negative impact on song complexity. Large colorful species were found to sing less complex songs. This result supports the hypothesis of a trade-off between costly traits and their likely intense signal function. This study contributes to a better understanding of how sexual selection influences the diversification of traits. In addition, we found that despite the relatively uniform size, the general negative correlation between body size and song frequency can be recovered. Some song traits are further influenced by distribution and thus by interspecific differences in climate niche. Full article

Statocyst anatomy and fine morphology in Norwegian lobster (Nephrops norvegicus) are studied for the first time using scanning and transmission electron microscopy. N. norvegicus exhibits sensory setae projecting from the statocyst inner cavity floor into a mass of sand granules (statoconia) embedded in a gelatinous substance. The setae are distributed in four areas: a curved field made up of an inner single row and an outer double row that run on a circle around the medial and lateral rim of the central depression, a small setal field in the posterior part, a large setal field, opposite to the small field, and a short row, running internally and lying parallel to the inner single row, next to the small setal field. A study of the fine morphology of the statocyst sensory setae shows that the structure of the setae in the different areas is similar, with a bulb (the proximal portion of the sensillum), a setal shaft, a tooth (the smooth portion of the bulb), a fulcrum (a transverse fold), and filamentous hairs. The hair cells are firmly implanted within the cuticular layer. Although the type of innervation of the statocyst was not determined in the present study, the close taxonomic position of the lobster to that of the crayfish and crab would suggest that the setae in N. norvegicus are pure mechanoreceptors rather than sensory cells. Full article

Bats play a pivotal role in maintaining ecological balance, and studying their behaviors offers vital insights into environmental health and aids in conservation efforts. Determining the presence of various bat species in an environment is essential for many bat studies. Specialized audio sensors can be used to record bat echolocation calls that can then be used to identify bat species. However, the complexity of bat calls presents a significant challenge, necessitating expert analysis and extensive time for accurate interpretation. Recent advances in neural networks can help identify bat species automatically from their echolocation calls. Such neural networks can be integrated into a complete end-to-end system that leverages recent internet of things (IoT) technologies with long-range, low-powered communication protocols to implement automated acoustical monitoring. This paper presents the design and implementation of such a system that uses a tiny neural network for interpreting sensor data derived from bat echolocation signals. A highly compact convolutional neural network (CNN) model was developed that demonstrated excellent performance in bat species identification, achieving an F1-score of 0.9578 and an accuracy rate of 97.5%. The neural network was deployed, and its performance was evaluated on various alternative edge devices, including the NVIDIA Jetson Nano and Google Coral. Full article

The ongoing biodiversity crisis, driven by factors such as land-use change and global warming, emphasizes the need for effective ecological monitoring methods. Acoustic monitoring of biodiversity has emerged as an important monitoring tool. Detecting human voices in soundscape monitoring projects is useful both for analyzing human disturbance and for privacy filtering. Despite significant strides in deep learning in recent years, the deployment of large neural networks on compact devices poses challenges due to memory and latency constraints. Our approach focuses on leveraging knowledge distillation techniques to design efficient, lightweight student models for speech detection in bioacoustics. In particular, we employed the MobileNetV3-Small-Pi model to create compact yet effective student architectures to compare against the larger EcoVAD teacher model, a well-regarded voice detection architecture in eco-acoustic monitoring. The comparative analysis included examining various configurations of the MobileNetV3-Small-Pi-derived student models to identify optimal performance. Additionally, a thorough evaluation of different distillation techniques was conducted to ascertain the most effective method for model selection. Our findings revealed that the distilled models exhibited comparable performance to the EcoVAD teacher model, indicating a promising approach to overcoming computational barriers for real-time ecological monitoring. Full article

Although fire is a natural phenomenon in the dynamics of some biomes around the world, it can threaten the biodiversity of certain ecosystems. Climate change and the expansion of anthropogenic activities have drastically increased the occurrence of large-scale burnings worldwide. The 2020 fire events in the Pantanal marked a historically unprecedented record, burning an area of approximately 40,000 km². However, how fires affect the local wildlife has yet to be evaluated. The aim of this study was to investigate the recovery of the avifauna in the Pantanal of Mato Grosso by comparing data selected from a previous study conducted between 2014 and 2016 with data collected in burned areas nine to twelve months after the fire. We compared diversity and community composition, investigated the influence of species trait foraging guild, foraging strata, and body mass on their response to fire, and complemented it with species’ individual responses. Bird richness and Shannon diversity were lower in burned areas, and the composition significantly varied between burned and unburned areas. The species’ response toward burned and unburned areas was significantly mediated by their traits, with smaller, piscivorous, omnivorous, ground and water, and midstory to canopy species being the most sensitive toward the environmental changes caused by the fire. Thirty-three species showed a negative response toward burned areas, but 46 species showed the opposite response, and 24 species were similarly abundant in unburned and burned areas. The present study is the first evaluation of the response of birds to the extreme fire events in the Pantanal and provides valuable insight into the recovery and resilience of local avifauna. Full article