Bird Sounds Research Articles

Impacts of Eco-Friendly Environmental Designs on Health and Well-Being of Patients in Hospitals

Homeopathic settings like hospital reception hall can increase a patient’s nervousness level as well as mental and physical reactions to their present state. This study is aimed at evaluating the use of environmental design, precisely the design that integrates fundamentals of the natural environment, in hospitals to reduce nervousness, hypertension and heartbeat rates of waiting patients. Depictions of landscape and the natural environment are known to restore feasible bonds between man and his environment, consequently, the influences of environmental design on patient’s reactions are rated and examined. In a bid to examine these assumptions about 145 persons were sampled. They were later classified into control and experiment clusters of males and females. The designed environment was subjected to experimental fields such as natural elements, green plants, sounds of waterfalls and birds. Both control and experimental fields were tested before and after the experiment. The results indicated that a designed hospital’s reception hall room immensely influences the decreased rate of patient nervousness (p< 0.001), hypertension (p< 0.001) and heartbeat rate (0.001). We propose that using an environmental design for homeopathic treatment centers can decrease the level of nervousness in patients and can lead to a patient’s recovery. Keywords: Architectural Design, Environmental Design, Nervousness, Hypertension, Heartbeat Rate, Stress

A Novel Bird Sound Recognition Method Based on Multifeature Fusion and a Transformer Encoder.

Birds play a vital role in the study of ecosystems and biodiversity. Accurate bird identification helps monitor biodiversity, understand the functions of ecosystems, and develop effective conservation strategies. However, previous bird sound recognition methods often relied on single features and overlooked the spatial information associated with these features, leading to low accuracy. Recognizing this gap, the present study proposed a bird sound recognition method that employs multiple convolutional neural-based networks and a transformer encoder to provide a reliable solution for identifying and classifying birds based on their unique sounds. We manually extracted various acoustic features as model inputs, and feature fusion was applied to obtain the final set of feature vectors. Feature fusion combines the deep features extracted by various networks, resulting in a more comprehensive feature set, thereby improving recognition accuracy. The multiple integrated acoustic features, such as mel frequency cepstral coefficients (MFCC), chroma features (Chroma) and Tonnetz features, were encoded by a transformer encoder. The transformer encoder effectively extracted the positional relationships between bird sound features, resulting in enhanced recognition accuracy. The experimental results demonstrated the exceptional performance of our method with an accuracy of 97.99%, a recall of 96.14%, an F1 score of 96.88% and a precision of 97.97% on the Birdsdata dataset. Furthermore, our method achieved an accuracy of 93.18%, a recall of 92.43%, an F1 score of 93.14% and a precision of 93.25% on the Cornell Bird Challenge 2020 (CBC) dataset.

One-step progressive representation transfer learning for bird sound classification

Most bird sound classification methods are based on supervised learning, which requires a large amount of labeled data for neural network models to establish the mapping relationship between bird sounds and labels. With the advent of self-supervised learning methods, neural network models can learn more general representations from unlabeled raw data and perform well on downstream tasks compared with fully supervised learning. In this study, we find that the self-supervised, pretrained representations can be transferred to the bird sound classification task. Furthermore, the model trained through self-supervised representation learning achieves a higher recognition rate after fine-tuning compared with the model based on supervised classification learning. However, this improvement in performance comes at the cost of the pretraining time amount. Considering these problems, we propose a one-step progressive representation transfer learning method for bird sound classification. This method integrates self-supervised representation and supervised classification learning into a two-branch network and uses a time-dependent loss weight transfer strategy to transfer bird sound, and self-supervised representation learning to bird sound classification learning. By using this method, the model emphasizes self-supervised representation learning during the early stages of training to maximize the similarities among bird sounds across different data augmentation versions. By utilizing the loss weight transfer strategy, the self-supervised bird sound representation learning transitions to supervised bird sound classification learning, thus enabling the model to acquire specific bird sound classification capabilities in the later stages of training. Experiments using the dataset Birdsdata demonstrate that our method outperforms both supervised classification and self-supervised classification learning methods.

SiulMalaya: an annotated bird audio dataset of Malaysia lowland forest birds for passive acoustic monitoring

The laborious point count method of conducting bird surveys is still a common practice in Malaysia. An alternative method known as passive acoustic monitoring (PAM) is deployed in many countries by placing sound recorders at surveying sites to collect bird sounds. Studies revealed that the number of bird densities counted by human observers was agreeable with those obtained using PAM. However, one of the most essential gaps in conducting PAM is the lack of expert-verified bird-call databases. Therefore, the aim of this study is to construct the first annotated Malaysia lowland forest bird sounds called SiulMalaya to be used as ground-truth datasets for PAM-related activities. The raw bird sounds dataset was downloaded from Macaulay Library using the eBird platform. Data pre-processing was done to produce annotated audio tracks that can be used as training datasets for bird classification. SiulMalaya dataset was further validated by two bird experts from the Department of Wildlife and National Parks, Malaysia. A bird identification experiment was carried out to assess and validate SiulMalaya dataset using a convolutional neural network (CNN) learning model. Even though the accuracy of bird identification is slightly above 50%, the annotated dataset is shown to be viable for PAM-related operations.

SiulMalaya: an annotated bird audio dataset of Malaysia lowland forest birds for passive acoustic monitoring

The laborious point count method of conducting bird surveys is still a common practice in Malaysia. An alternative method known as passive acoustic monitoring (PAM) is deployed in many countries by placing sound recorders at surveying sites to collect bird sounds. Studies revealed that the number of bird densities counted by human observers was agreeable with those obtained using PAM. However, one of the most essential gaps in conducting PAM is the lack of expert-verified bird-call databases. Therefore, the aim of this study is to construct the first annotated Malaysia lowland forest bird sounds called SiulMalaya to be used as ground-truth datasets for PAM-related activities. The raw bird sounds dataset was downloaded from Macaulay Library using the eBird platform. Data pre-processing was done to produce annotated audio tracks that can be used as training datasets for bird classification. SiulMalaya dataset was further validated by two bird experts from the Department of Wildlife and National Parks, Malaysia. A bird identification experiment was carried out to assess and validate SiulMalaya dataset using a convolutional neural network (CNN) learning model. Even though the accuracy of bird identification is slightly above 50%, the annotated dataset is shown to be viable for PAM-related operations.

The effects of the natural visual-aural attributes of urban green spaces on human behavior and emotional response.

Nature-based solutions (NBS) have been used to address a wide range of urban environmental challenges, an important aspect of which is to improve human health and well-being. However, most relevant studies focus either on what positive influences nature may have or on identifying what natural factors can have these benefits. Few have investigated the sensory composition of nature and the effects of nature in different sensory aspects on human health. Setting out from the multi-sensory perspective, this study aims to explore human behavior and emotional response from visual and aural contact with urban nature. Taking Jiangjia Art Garden in Chengdu as an example, natural attributes such as its visual (landscape) and aural (sound source) characteristics as well as people's activities (behavioral responses) were measured by on-site mapping analysis. This was done while a questionnaire-based survey was conducted to investigate people's emotional responses regarding their overall satisfaction, pleasantness, calm, and agreeableness. The results indicated that nature-dominated visual landscapes such as grassland, waterscapes, and woodlands, as well as natural sounds such as bird sounds, chirp sounds, and wind sounds were found to be positively correlated to the vitality of activities and people's emotional status. Regarding behavioral responses, it was shown that grasslands and woodlands are more likely to be attractive places for recreation, and the vitality measured became extremely high when these two were paired with lakes. As for the emotional responses, people's perceived overall satisfaction, calm, and agreeableness were equally reflected in their behavioral patterns, suggesting a strong relationship with natural factors. The research findings were visually presented in behavior and emotional maps to provide direct cues of informing the future design of high-quality urban green spaces and promoting the application of aural-visual experience in the design of urban nature areas.

A lightweight multi-sensory field-based dual-feature fusion residual network for bird song recognition

Bird song recognition plays an important function in ecosystem balance monitoring, biodiversity detection, and biodiversity conservation. Due to the complexity of the natural environment, based on deep learning, there is a problem of information loss in extracting audio features with a single filter. Identifying bird sounds efficiently and quickly is still a challenge. To address this problem, a lightweight multi-sensory field dual-feature fusion residual network (LDFSRE-NET) is proposed in this paper. Firstly, using the feature extraction filters based on Mel and SincNet to extract birdsong’s low-frequency and timbre information. The proposed dual-feature fusion module (FFMS) is used to fuse the low-frequency and timbre information with the differences between the two feature sets. Secondly, the double-layer residual module (DBNet), connected by basicblock and downblock, is used as the backbone network for bird song recognition to improve the training speed. To improve the different perceptual fields of the backbone network, the 3 × 3 convolutional modules in the basicblocks of the two residual modules are replaced with a Diverse Branch Block. They make the network performs better on recognition tasks under complex situations of multiple branches. Then, the ShuffleAttention attention module is embedded between the two layers of the residual module for transferring its valid information, enhancing the spectrogram ripple feature, and further improving the network’s recognition performance. Finally, extensive experiments are conducted on three datasets: the self-built 30-class bird song dataset (Birdselfdata), the public datasets Birdsdata and Urbansound8K. The model proposed in this paper surpasses the state-of-the-art sound recognition model methods in terms of efficiency and accuracy. The recognition accuracy on these three datasets of this model are 96.75%, 96.46%, and 97.98%, with the F1-score of 96.79%, 96.39%, and 97.88%.

Effects of landscape and distance in automatic audio based bird species identification.

The present work focuses on how the landscape and distance between a bird and an audio recording unit affect automatic species identification. Moreover, it is shown that automatic species identification can be improved by taking into account the effects of landscape and distance. The proposed method uses measurements of impulse responses between the sound source and the recorder. These impulse responses, characterizing the effect of a landscape, can be measured in the real environment, after which they can be convolved with any number of recorded bird sounds to modify an existing set of bird sound recordings. The method is demonstrated using autonomous recording units on an open field and in two different types of forests, varying the distance between the sound source and the recorder. Species identification accuracy improves significantly when the landscape and distance effect is taken into account when building the classification model. The method is demonstrated using bird sounds, but the approach is applicable to other animal and non-animal vocalizations as well.

Semiotic Dimension Deconstruction in the First Movement of "Spring" by Vivaldi

Music is a means of expressing feelings and aesthetics in the human mind and heart. Through increasing human creativity, this media for expression comes in many types, one of which is program music, whose compositional construction is based on the composer's imagination to describe a character, atmosphere, or an event. Allegro of “Concerto No. 1 in E major, Op. 8, RV 269: Spring (La primavera)”, as the first movement of the program music The Four Seasons from Vivaldi, is famous for depicting the atmosphere of spring filled with birdsong, the wind blowing, to the sound of the river flowing. Therefore, this study intents to thoroughly examine those representations of this atmosphere through the deconstruction of the semiotic dimension. As an inductive qualitative research, Peirce's semiotic theory and the descriptive analysis data method are applied. Based on Peirce's semiotic theory, the description of the spring atmosphere is present in interpretant through the imitation of bird sounds, river flow, and storms; harmonic progressions, melodic motifs, musical technique ornaments, and collective structures in objects; as well as sonnets in representamen. Thus, it can be summarized that the illustration of the atmosphere in the title and sonnet is closely related to the music notation, meaning they are inseparable. In the past few years, an akin exploration that focuses on Vivaldi's works through the semiotic perspective was absent; hence, this study plays a huge part in its research contribution to the field of knowledge.

Bone aerophones from Eynan-Mallaha (Israel) indicate imitation of raptor calls by the last hunter-gatherers in the Levant

Direct evidence for Palaeolithic sound-making instruments is relatively rare, with only a few examples recorded from Upper Palaeolithic contexts, particularly in European cultures. However, theoretical considerations suggest that such artefacts have existed elsewhere in the world. Nevertheless, evidence for sound production is tenuous in the prehistoric archaeological record of the Levant, the study of music and its evolution being sparsely explored. Here we report new evidence for Palaeolithic sound-making instruments from the Levant with the discovery of seven aerophones made of perforated bird bones in the Final Natufian site of Eynan-Mallaha, Northern Israel. Through technological, use-wear, taphonomic, experimental and acoustical analyses, we demonstrate that these objects were intentionally manufactured more than 12,000 years ago to produce a range of sounds similar to raptor calls and whose purposes could be at the crossroads of communication, attracting hunting prey and music-making. Although similar aerophones are documented in later archaeological cultures, such artificial bird sounds were yet to be reported from Palaeolithic context. Therefore, the discovery from Eynan-Mallaha contributes new evidence for a distinctive sound-making instrument in the Palaeolithic. Through a combined multidisciplinary approach, our study provides important new data regarding the antiquity and development of the variety of sound-making instruments in the Palaeolithic at large and particularly at the dawn of the Neolithic in the Levant.

Acoustic niche partitioning among seven cuckoo species in a forest in eastern China

Acoustic communication among birds plays an important role in attracting mates and defending territories. For the successful transmission of songs, individuals of different species often avoid singing at the same time to reduce acoustic interference from background noise and overlapping signals from heterospecifics. Such behavioural acoustic niche partitioning may occur especially among closely related species due to their ecological similarities. In this study, we recorded bird sounds in a subtropical forest in China in May–June 2019 and detected seven cuckoo species. Extracting characteristics of the cuckoo calls, we found that only four of the 21 pairs of species overlapped in frequency range, and 19 pairs were classified accurately using a linear discriminant analysis classifier based on their features. The remaining two species pairs could be separated based on temporal or spatial distribution patterns. We also analysed the temporal distribution patterns and overlap time of the calls, finding that the seven species exhibit partitioning in at least one of three acoustic dimensions (site, frequency, activity time). We conclude that the seven sympatric cuckoo species were strongly partitioned in acoustic signal space and minimally masked each other's signals.

Mimetic Dimensions of Bird-Human Interactions: The Use of Bird Sound Imitations among Estonian Birders

Abstract This paper explores bird sound imitation as a particular type of interspecies interaction. Using questionnaires, interviews, and participatory observations, a survey was conducted among Estonian birders to find out about the prevalence of the practice, the diversity of imitated species, the means of imitation, and the attitudes of birders towards the use of recordings in the field. The study found that 55 species of birds from 11 orders were imitated and using one’s own voice was the most common way of imitating birds. The choice of the method of imitation depended on the purpose and context of imitation. Most birders supported the use of playbacks for scientific purposes, but not for daily birding. With the easy availability of playback technologies, there are increased concerns about the ubiquitous presence of disturbing factors. At the same time, however, the technological boundlessness is balanced by the heightened ethical self-reflection of birders.

Connectedness to Nature, Well-Being and Presence of Birds

Connectedness to Nature represents a growing area of interest in the latest years because it could have implications in human behavior. In addition, another type of implications studied in people have been the sounds of birds. The aim of this literature review was to analyze the state of knowledge about Connectedness to Nature and birds, as well as its link with variables related to well-being to identify gaps and directions for further research. We reviewed 41 papers published between 2011 and 2021. Papers were found in 29 journals with studies from 16 countries. Eighty-five percent of the papers used an experimental design and there is a trend of increasing publications over time. Our results show that Connectedness to Nature is linked to variables related to well-being, and the presence of birds (or their perception) contributes to explain the relationship. Therefore, more research on the subject is needed because there is evidence that contradicts some findings. Also, research is needed in different bird species, sounds, different cultures and local contexts, thus, it is necessary to study rural and urban areas. In addition, research is needed in children and teenagers who have been very little represented. Finally, it is necessary to have more information from Latin American countries as they represent the most diverse in bird species and to be able to compare with more studied regions like Europe and North America.

Anthropogenic noise events perturb acoustic communication networks

Anthropogenic noise sources impact ecological processes by altering wildlife behavior and interactions with cascading impacts on community structure. The distribution and magnitude of such noise has grown exponentially over the past century, and now inundates even remote areas. Here we investigate biological responses to prolific, anthropogenic noise sources associated with the physical presence of the source (vehicle noise and human voices) and disconnected from it (aircraft overflight). Bioacoustic responses to these noise sources were documented at 103 sites in 40 U. S. National Park units. The presence of bird sounds was noted in 10-s audio samples every 2 min, for 8 days at each site and related to the presence of human voices, vehicle noise, and aircraft noise in the same and preceding samples. Generalized additive models were used to fit smoothing splines to weight the influence of noise in past samples on the probability of detecting bird sounds in the present sample. We found that the probability of hearing birds increased immediately following noise events, and decreased about 2 h after the event. The negative effects were persistent more than 3 h after a noise event. The persistence of these responses – especially for noise from jets that were many kilometers distant – raises questions about the functional significance and ecological consequences of this altered activity, particularly in light of the widespread and diverse habitats in this study and ubiquity of the noise sources evaluated.

Bird Sounds Psychological Restorative Effect on The Visitors of Bogor Botanical Garden

Stress can be defined as psychological and physical tension caused by physical, emotional, social, economic, and occupational, events, or experiences that are difficult to manage or endure. Bird sounds can be a potential solution to reduce stress levels. This study aimed to analyze the effect of bird sounds as a stress restorative on Bogor Botanical Garden visitors. A survey of 100 visitors of Bogor Botanical Garden was conducted based on the Perceived Stress Scale and Perceived Restorativeness Soundscape Scale. Data on respondent characteristics were analyzed using descriptive analysis, the relationship between stress levels and perceived stress restorative effect of bird sound was analyzed using Pearson correlation analysis. The analysis showed that 78% of respondents had moderate to high perceived stress levels and 98% of respondents rated the degree of restoration from bird sounds to be moderate to high. The correlation analysis revealed a negative relationship between the stress level and bird sounds' perceived restorative effect. The older the respondents and the more frequently they visited Bogor Botanical Garden, the higher the perceived stress restorative effect from bird sound.

A Successful Crowdsourcing Approach for Bird Sound Classification

Automated recorders are increasingly used in remote sensing of wildlife, yet automated methods of processing the audio remains challenging. Identifying animal sounds with machine learning provides a solution, but optimizing the models requires annotated training data. Producing such data can require much manual effort, which could be alleviated by engaging masses to contribute to research and share the workload. Birdwatchers are experts on identifying bird vocalizations and form an ideal focal audience for a citizen science project aiming for the required multitudes of annotated avian audio data. For this purpose, we launched a web portal that was targeted and advertised to Finnish birdwatchers. The users were asked to complete two kinds of tasks: 1) classify if a given bird sound belonged to the focal species and 2) classify all the bird species vocalizing in 10-second audio clips. In less than a year, the portal achieved annotations for 244,300 bird sounds and 5,358 clips, and attracted, on average, 70 visitors on daily basis. More than 200 birdwatchers took part in the classification tasks, of which 17 and 4 most dedicated users produced over half of the sound and clip classifications, respectively. As expected of birder experts, the classifications among users were highly consistent (mean agreement scores between 0.85–0.95, depending on the audio type) and resulted in high-quality training data for parameterizing machine learning models. Feedback about the web portal suggested that additional functionality such as increased freedom of choice would increase user motivation and dedication.

Nature Sounds for Stress Recovery and Healthy Eating: A Lab Experiment Differentiating Water and Bird Sound

This lab-based study tested whether nature sounds can lead to less stress reactivity, better stress recovery, less stress-induced eating and healthy food choice stimulation, while differentiating between bird and water sounds. Before (5 min) and after (8 min) the Trier Social Stress Test, 59 participants (47% men, 18–30 years) were exposed to one of three soundtracks: birds, streaming water, or wind as control. Group differences were tested on negative affect, salivary cortisol, heart rate variability, hunger, food craving, snack intake and influence expectations. Both bird and water sounds led to better cortisol recovery (not reactivity) and were reported to be more stress-reducing than wind only. The recovery effect was highest for water sounds. No differential sound effects were found for the food variables. The results confirm the potential implementation of bird and water sounds for stress restoration but future research should test the effects (especially on diet) in real-life settings.

Acoustic Classification of Bird Species Using an Early Fusion of Deep Features

Bird sound classification plays an important role in large-scale temporal and spatial environmental monitoring. In this paper, we investigate both transfer learning and training from scratch for bird sound classification, where pre-trained models are used as feature extractors. Specifically, deep cascade features are extracted from various layers of different pre-trained models, which are then fused to classify bird sounds. A multi-view spectrogram is constructed to characterize bird sounds by simply repeating the spectrogram to make it suitable for pre-trained models. Furthermore, both mixup and pitch shift are applied for augmenting bird sounds to improve the classification performance. Experimental classification on 43 bird species using linear SVM indicates that deep cascade features can achieve the highest balanced accuracy of 90.94% ± 1.53%. To further improve the classification performance, an early fusion method is used by combining deep cascaded features extracted from different pre-trained models. The final best classification balanced accuracy is 94.89% ± 1.35%.

Bird sound classification based on ECOC-SVM

Birds are an important part of the ecosystem. Knowing the number of existing bird species is important for maintaining ecological balance. The sounds of birds contain rich biological features. The classification of bird species based on their sounds helps to protect the ecological environment. In this study, a fused classification method based on the Error Correction Output Coding (ECOC) and Support Vector Machines (SVM) is investigated to classify 11 species of birds. The Mel Frequency Cepstrum Coefficients (MFCC) of bird sound are extracted as acoustic feature. The ECOC-SVM is compared with Random Forest (RF), Gaussian Mixture Model (GMM) and a multi-layer perceptron neural network (MLP-NN) and a convolutional neural network (CNN) for the bird sound classification. The proposed ECOC-SVM model is validated on the open dataset available from the Macaulay Library at Cornell University. The ECOC-SVM achieves the best classification result and relatively low computational cost among all discussed classifiers on the test set with 100 % accuracy and 52 ms prediction time. The results show that the proposed ECOC-SVM model could well apply on the bird sound classification of multiple species with excellent performance and relatively low computational cost.

Analysis of vocal communication in the genus Falco

Vocal learning occurs in three clades of birds: hummingbirds, parrots, and songbirds. Examining vocal communication within the Falconiformes (sister taxon to the parrot/songbird clade) may offer information in understanding the evolution of vocal learning. Falcons are considered non-vocal learners and variation in vocalization may only be the result of variation in anatomical structure, with size as the major factor. We measured syringes in seven Falco species in the collection at the American Museum of Natural History and compiled data on weight, wing length, and tail length. Audio recordings were downloaded from several libraries and the peak frequency and frequency slope per harmonic number, number of notes in each syllable, number of notes per second, duration of each note, and inter-note duration was measured. Mass, wing length, and syringeal measurements were strongly, positively correlated, and maximum frequency is strongly, negatively correlated with the size. Frequency slope also correlates with size, although not as strongly. Both note and inter-note length vary significantly among the seven species, and this variation is not correlated with size. Maximum frequency and frequency slope can be used to identify species, with the possibility that bird sounds could be used to identify species in the field in real time.