Bird Sounds Research Articles

The first report of syllable analysis of the chattering lory (Lorius Garrulus (Linnaeus, 1758)) in the crooked beak sanctuary of Koli Village, Tidore Islands City, North Maluku

The Chattering lory is an endemic bird with a restricted range in North Maluku. The crooked-beaked bird is one of the world's most popular types of domesticated birds, which negatively affects its long-term viability. The population estimate for chattering lory birds is between 46,360 and 295,540 heads. Poaching is the most significant factor contributing to population decline. An estimated 16,000 chattering lory are captured and sold annually. This study intends to analyze the syllables of bird sounds, as bird-sound-related research is still uncommon. The data collected from a Voice Recording of the chattering lory (Lorius garrulus) was then analyzed using Avisoft-SASlab Lite software. This study was conducted by recording bird sounds. The recording process (Analog Recording) is carried out within a specific time interval to record the birds' sounds multiple times. Bird sounds are recorded in the morning (07:00 to 10:00 WIT). The results indicated that the chattering lory's 131.4-second-long call consists of 18 syllables and four elements. The duration of a syllable varies from 0.51 to 0.66 seconds, and the duration between syllables ranges from 1.31 to 16.09 seconds. Also, the variable is the frequency of each upper and lower element. The lower element's frequency ranges from 100 to 12,100 kHz, while the upper element's frequency ranges from 1,500 to 18000 kHz.

Classification of Bird Sounds Using the Mel-Frequency Cepstral Coefficient (MFCC) and K-Nearest Neighbor (KNN) Methods

Classification of Bird Sounds Using the Mel-Frequency Cepstral Coefficient (MFCC) and K-Nearest Neighbor (KNN) Methods

Bird sound recognition based on adaptive frequency cepstral coefficient and improved support vector machine using a hunter-prey optimizer.

Bird sound recognition is crucial for bird protection. As bird populations have decreased at an alarming rate, monitoring and analyzing bird species helps us observe diversity and environmental adaptation. A machine learning model was used to classify bird sound signals. To improve the accuracy of bird sound recognition in low-cost hardware systems, a recognition method based on the adaptive frequency cepstrum coefficient and an improved support vector machine model using a hunter-prey optimizer was proposed. First, in sound-specific feature extraction, an adaptive factor is introduced into the extraction of the frequency cepstrum coefficients. The adaptive factor was used to adjust the continuity, smoothness and shape of the filters. The features in the full frequency band are extracted by complementing the two groups of filters. Then, the feature was used as the input for the following support vector machine classification model. A hunter-prey optimizer algorithm was used to improve the support vector machine model. The experimental results show that the recognition accuracy of the proposed method for five types of bird sounds is 93.45%, which is better than that of state-of-the-art support vector machine models. The highest recognition accuracy is obtained by adjusting the adaptive factor. The proposed method improved the accuracy of bird sound recognition. This will be helpful for bird recognition in various applications.

Reliable Sound Re-labeling Approach for Bird Sound Classification

Passive acoustic monitoring has become an effective and economically scalable solution for wildlife monitoring in recent years, especially for population monitoring of endangered birds in hardly accessible and high-elevation areas. As sound recorders are deployed on the field for extended periods (months), continuous sound streams are often complex in nature, with noises and intermittent signals. Generally, it is prohibitively expensive to label bird sounds with the exact onset and offset time, thus, during training, the data is often provided with only presence/absence labeling (weak labeling) that states which bird species are present in each long recording without temporal information. During test time, it is, however, desirable to provide fine-grained detection in short audio segments. To bridge the gap between the difference of weak labels used for training and strong labels used for testing, we propose a re-labeling approach with two stages: (1) we train a model with weak labeling; and (2) using the model obtained from stage 1, we generate labels for short audio segments and retrain the model on short audio segments with the newly generated labels. We applied our approach in both classification and sound event detection and achieved consistently good performance across multiple random seeds. In BirdCLEF 2022, our model ranked in the top 1.1%, the 9th best entry out of the total 807 entries in the competition.

Wild Bird Species Identification Based on a Lightweight Model with Frequency Dynamic Convolution

The sound recognition technology is used to count bird speciespopulation to provide accurate data for population ecology and conservation biology research. Bird species can be identified by spectrogram of bird’s sounds. The existing Convolutional Neural Network(CNN) is not good at mining the relationship between features in time-frequency tasks, and the existing CNN has more parameters and complicated calculation, so existing models are not suitable for deployment in an actual field environment. In order to fill this gap, this paper proposes a lightweight model with frequency dynamic convolution for bird species identification. We use frequency dynamic convolution innovatively to better capture features of bird sounds at different frequencies. First of all, we replaced two-dimensional convolution with frequency-dynamic convolution in order to achieve not-shift invariance of the bird sound’s spectrogram, so that we can effectively capture the feature differences of spectrogram in different frequency bands. Then, we replaced part of the Squeeze and Excitation(SE) attention mechanism with the Coordinate Attention(CA) attention mechanism in order to get more comprehensive global information. Finally, the feature fusion module was used to fuse the local and global features. In addition, we built a datasets containing 160 bird sounds, improving the generalization ability of the model. The experimental results show that our model has good generalization ability and is superior to the existing Lightweight CNN, and obtained better results in top1 accuracy and top5 accuracy.

Analyzing and Comparing Frequency of the Birds Sound Spectrum using Audacity Software in Practicum Activity

In the science learning process especially sound waves concept, experiments are needed that can help someone in gaining a meaningful learning and using technology. In this study, the aim is to analyze and compare the bird sound frequency assisted by Audacity software. The subjects used are three different bird sound (Murai Batu’s sound as the main subject while the Love Bird and Kenari’s sound as the compared subject). The implementation of this study uses several tools such as a microphone, Audacity software on a laptop and bird sounds. This experiment was carried out by bringing the microphone closer to the bird with 15 cm, so that the sound was captured by the microphone, then transferred to the laptop and read by the Audacity software. Furthermore, the data recorded in Audacity were analyzed. From the results of the study, it can be concluded that combination of bird sounds and audacity tools can be used in practicum, can read and capture bird sound waves effectively in analyzing and comparing the bird sound frequency and spectrum in the software. Thus, it tends to be utilized as one of the learning media in practicum on sound wave material at secondary school.

Moral Message Of Nature's Sustainability: Semiotic Analysis Of Alam Menyapa On Audio-Visual Music Composition

Alam Menyapa is a musical composition which is a blend of Western and traditional music from various countries. The idea for Alam Menyapa came from the composition Song of the Birds, which was once used as therapeutic music for drug-affected patients, at the Mutiara Abadi Foundation in Binjai City. One of the uniqueness of Alam Menyapa is the adoption of natural sounds, such as the sounds of various birds, the sound of river water, the sound of wind blowing, and other animal sounds, which are then digitally combined with various musical instruments. The method used is descriptive qualitative, collecting data with literature, observation, interviews and documentation. The data analysis technique used is interactive analysis from Milles and Hubermann. The results of this study indicate that Alam Menyapa has a simple musical concept which includes: 1) The musical instruments used are a blend of Western and traditional music through digital music, 2) Musical elements; playing rhythmic patterns that complement each other, simple melodies with simple dynamic signs 3) Forms of presentation through recordings of natural sounds included in digital music and audio-visual. 4) The symbolic meaning of balanced natural life, 5) The aesthetic expression of harmony and simple chords, and 6) The educational value contained is that the sounds of nature can be applied to digital music with simple melodies and harmonies. The theory of meaning or symbols used by the author in conducting research is the theory of Roland Barthes. The result of the research is an analysis of Indonesian music composition with the aim that more and more works by Indonesian composers will be introduced to the world through analysis.

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.

AMResNet: An automatic recognition model of bird sounds in real environment

Birds are biological indicators reflecting environmental quality and its changes, so ecologists devote a great deal of attention to monitor their population trends. Automated acoustic recognition is regarded as an important technology to support bird monitoring and conservation activities. However, traditional bird sounds recognition methods have problems such as high cost, long time consuming and low precision. To address these problems, a novel automatic recognition model of bird sounds was proposed. The proposed model (AMResNet) was based on the combination of attentional mechanism and residual networks, which can automatically extract and select high-dimensional features to achieve a high classification accuracy. Attentional mechanism can improve the recognition efficiency by assigning appropriate weights to channels and space. Residual network can alleviate the problem of gradient disappearance and increase the information flow by skip connections. More importantly, an efficient combined feature was adopted in this paper, to give a more comprehensive representation of bird sounds. By trained and tested by 10-fold cross-validation in 12651 bird sound samples from the real environment, the AMResNet with combined features was proved to be appropriate for bird sound taxonomic problems, and dramatically outperform over other eight models, which contains two traditional models, a forward neural network, four main deep learning models and a latest vision transform model. The proposed model achieved a classification accuracy of 92.6%, which was 3.1% higher than the highest of other eight models, and it also achieved the best results in precision (97.6%), recall (97.3%) and F1-score (97.1%) across the 19 species.

Bird signs can be important for ecocultural conservation by highlighting key information networks in people–bird communities

AbstractThe ways people think, feel, speak about, and act in and with environments are inextricably intertwined with the well-being of other living things, including birds. We report on the kinds of messages contained in 598 examples of locally-defined signs from 498 bird taxa from 169 sources and 123 ethnolinguistic groups. Using Peirce’s three sign forms: symbolic, iconic, and indexical, we analyze one aspect of human–bird interactions: that of reading bird sign for ecological and social interpretations. Understanding ecological semiotic nuance is important for translating between local, regional, and global science, and for respecting autonomous processes of local people attributing value or lack thereof to birds and their habitats. Over one-third of the signs in our sample (216; 36%) were specifically described as omens of some kind, commonly of death, illness, or something “bad”. Three modes of message delivery account for the majority of the data: predicting (60%), bringing (15%; including news, rain, luck), and indicating (15%; including seasonal change, fruit ripening, animals). Reading birds to predict weather (especially rain) was common, as was listening to and interpreting birds’ alarm calls warning of snakes or predators, and knowing that a certain bird indicates the presence of certain other animals, or of a water source. We collected 51 examples of warblish, the imitation or translation of bird sounds into non-onomatopoeic words. We argue for the amplification of ecocultural conservation (attending to histories of human–nonhuman relationships in place) to channel resources and land control to local and Indigenous managers who are immersed in relevant bird–people information networks. We discuss the importance of (1) reduction of uncertainty in local and hyper-local environments, (2) biocultural provocations in which birds fulfill important roles in human society, and (3) informational connectivity and locally-defined interspecies ethical relationships as key elements for inclusive and effective ecocultural bird conservation.

An Efficient Time-Domain End-to-End Single-Channel Bird Sound Separation Network.

Bird sounds have obvious characteristics per species, and they are an important way for birds to communicate and transmit information. However, the recorded bird sounds in the field are usually mixed, which making it challenging to identify different bird species and to perform associated tasks. In this study, based on the supervised learning framework, we propose a bird sound separation network, a dual-path tiny transformer network, to directly perform end-to-end mixed species bird sound separation in the time-domain. This separation network is mainly composed of the dual-path network and the simplified transformer structure, which greatly reduces the computational resources required of the network. Experimental results show that our proposed separation network has good separation performance (SI-SNRi reaches 19.3 dB and SDRi reaches 20.1 dB), but compared with DPRNN and DPTNet, its parameters and floating point operations are greatly reduced, which means a higher separation efficiency and faster separation speed. The good separation performance and high separation efficiency indicate that our proposed separation network is valuable for distinguishing individual birds and studying the interaction between individual birds, as well as for realizing the automatic identification of bird species on a variety of mobile devices or edge computing devices.

Exposure to Nature Sounds through a Mobile Application in Daily Life: Effects on Learning Performance among University Students.

Previous studies have revealed the restorative effects of exposure to natural environments on psychological well-being and cognitive performance. Recent studies have reported the effects of exposure to nature sounds (e.g., the sounds of birds, rainfall, and waves) through a mobile application on reducing students' mental fatigue and improving their cognitive performance. However, it remains unknown whether exposure to nature sounds through a mobile application may influence students' learning performance. To address the gap, we conducted a study with 71 university students. During the four-week intervention, 36 students in the experimental group were exposed to nature sounds through a free mobile application for at least 30 consecutive minutes per day when working on academic-related tasks; 35 students in the control group did not have such exposure when working on similar tasks. The results show that students in the experimental group outperformed those in the control group in their engagement in deep learning, frequency of academic procrastination, and academic self-efficacy. The findings reveal the promising effects of exposure to nature sounds through a mobile application on improving students' learning performance. The implications of the findings are discussed.

Urban park soundscapes: Spatial and social factors influencing bird and traffic sound experiences

Abstract Natural soundscapes experienced in parks are increasingly recognised as a valuable ecosystem service, yet urban parks soundscapes also commonly contain anthropogenic noise. While studies show bird calls can promote psychological restoration, the factors that might influence actual experiences of these sounds by individuals in urban parks are less clear. Equally, continual exposure to anthropogenic noise, such as vehicle traffic, is associated with negative health outcomes, but determinants influencing negative experiences of such sounds within a park soundscape are poorly understood. To address this gap we used an ex situ survey of over 4000 Australian residents and examined a range of spatial and social factors in influencing perceptions towards noticing and pleasantness of bird sounds and traffic noise within urban parks. The results indicate older age, recent park use, and valuing parks for uses such as exercising, socialising and to hear nature, were positively associated with pleasant bird sound experiences in parks. For traffic sounds, we found indicators of disadvantage, such as renting a home were associated with a higher likelihood of unpleasant experiences of traffic noise within parks. Notably, individuals using parks for social activities were still positively associated with pleasant bird sound experiences and less likely to perceive traffic sounds as unpleasant. Conversely, whilst those with greater nature‐relatedness had a strong positive association with pleasant bird sound experiences, they were more likely to perceive traffic as unpleasant. Overall, these findings suggest that whilst many types of park users can potentially experience the beneficial effects from bird sounds, the detrimental effects of traffic noise may constrain these benefits in certain social groups, particularly those of greater socio‐economic disadvantage. We discuss strategies to promote greater equity of therapeutic experiences of bird sounds in parks, whilst outlining traffic mitigation measures within urban parks. Read the free Plain Language Summary for this article on the Journal blog.

Ecology and evolution of bird sounds

Birds are among nature's most social animals. They are renowned for their group migrations, their cooperative foraging, their communal roosting, their synchronous breeding aggregations, their precise parent-offspring interactions, their coordinated group defenses and their intricate territorial and courtship rituals. In these and other contexts, and indeed in most moments of their lives, birds' capacities to navigate complex social demands and relationships can tip the balance between health or sickness, between reproductive success or failure, between life or death. It is thus no surprise that birds have evolved sophisticated systems for mediating social interactions. Foremost among these are communication signals, most evident in birds as songs, calls, color patterns and postural displays. These and other communication signals can transmit information about a signalers' status, motivations and possible future actions, for sensory and cognitive processing by signal receivers. In general, signals provide benefits for both signal senders and receivers. Consider the bright spring plumage of a male wood warbler who has established a breeding territory. The male's plumage pattern benefits him by signaling his 'ownership' of his territory, which can help him attract potential mates and preempt conflict with potential rivals. His plumage pattern also benefits his intended audiences: it informs females about the signaler's potential as a mate, and it informs other males about the degree of threat they might face were they to attempt a territory take-over. Communication signals are, in essence, a glue that maintains the cohesion of bird societies, and a currency that mediates sophisticated relationships within.

Effects of Soundscapes on Human Physiology and Psychology in Qianjiangyuan National Park System Pilot Area in China

The development of China’s national parks is still in the initial stage, and few scholars have studied the effects of soundscapes on human physiology and psychology from the perspective of the auditory senses in national parks. In this study, the Qianjiangyuan National Park System Pilot Area was taken as the research subject, physiological indicators of subjects were collected through a biopAC-MP150 multi-channel physiological instrument data platform, and the subjective psychological response of soundscapes was measured using a Likert scale. The results showed that the sound of water had the most significant effect on the heart rate and respiratory rate of the subjects. Agricultural sound had the greatest impact on the skin conduction levels, while conversation had the least overall impact on human physiology. There were significant differences in comfort, excitement, and significance among the different soundscapes (p < 0.001). The sounds of insects are more likely to elicit feelings of comfort and excitement, while the sounds of birds are more likely to arouse curiosity. No significant correlation was observed between the physiological indices and psychological indices. The study on the effects of different soundscapes on human physiology and psychology in China’s national parks will provide a basis for the decision makers of national parks to formulate more effective planning, design, and management policies regarding soundscapes.

Automatic Classification of Bird Sounds: Using MFCC and Mel Spectrogram Features with Deep Learning

Bird species identification is a relevant and time-consuming task for ornithologists and ecologists. With growing amounts of audio-annotated data, automatic bird classification using machine learning techniques is an important trend in the scientific community. Analyzing bird behavior and population trends helps detect other organisms in the environment and is an important problem in ecology. Bird populations react quickly to environmental changes, which make their real-time counting and tracking challenging and very useful. A reliable methodology that automatically identifies bird species from audio would therefore be a valuable tool for the experts in different scientific and applicational domains. The goal of this work is to propose a methodology to identify bird sounds. In this paper, we explore deep learning techniques that are being used in this domain, such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) to classify the data. In deep learning, audio problems are commonly approached by converting them into images using audio feature extraction techniques such as Mel Spectrograms and Mel Frequency Cepstral Coefficients (MFCCs). We propose and test multiple deep learning and feature extraction combinations in order to find the most suitable approach to this problem.

Forest quality assessment based on bird sound recognition using convolutional neural networks

Deforestation in Indonesia is in a status that is quite alarming. From year to year, deforestation is still happening. The decline in fauna and the diminishing biodiversity are greatly affected by deforestation. This paper proposes a bioacoustics-based forest quality assessment tool using Nvidia Jetson Nano and convolutional neural networks (CNN). The device, named GamaDet, is a portable physical product based on the microprocessor and equipped with a microphone to record the sounds of birds in the forest and display the results of their analysis. In addition, a Google Collaboratorybased GamaNet digital product is also proposed. GamaNet requires forest recording audio files to be further analyzed into a forest quality index. Testing the forest recording for 60 seconds at an arboretum forest showed that both products could work well. The GamaDet takes 370 seconds, while the GamaNet takes 70 seconds to process the audio data into a forest quality index and a list of detected birds.

Sliding-window based scale-frequency map for bird sound classification using 2D- and 3D-CNN

Bird’s call often contains distinctive information for discriminating different species. Previous studies have investigated various features for bird sound classification. This paper proposes a novel feature set for automatically classifying bird sounds. Specifically, a sliding window is first applied to the audio waveform for obtaining windowed signals, where five windows having the highest energy are selected. Then, orthogonal matching pursuit is applied to those windowed signal for extracting important Gabor atoms. Next, a multi-window scale-frequency map is constructed as the input to three different CNN models for bird sound classification. Experiments on two bird sound classification datasets demonstrate the effectiveness of our proposed framework for supplementing traditional audio time–frequency representations. Classification accuracy and F1-score on the 14-class bird sound dataset are 98.96% and 98.93%, respectively, which are obtained by 2D-CNN-v2 with ERB-scaled SFM as the input. For 18-class bird sound dataset, the highest accuracy and F1-score are 97.82% and 97.47%, respectively, where 2D-CNN-v2 is used with Bark-scaled SFM as the input. Moreover, 2D-CNN-v2 with Bark-scaled SFM as the input achieves the best performance for the combined data, and the highest accuracy and F1-score are 98.59% and 98.51%, respectively.

Two-Phase Sensor Decision: Machine-Learning for Bird Sound Recognition and Vineyard Protection

For a wireless sensor network consisting of numerous sensors, spread over a large area with no direct power supply, energy efficiency is of paramount importance. As most power is consumed by the communication module, special attention has to be paid to reduce communication needs as much as possible. The more data is sent, the larger the power requirement of the sensor module. Preprocessing can help in reducing the amount of data to send. However, it also consumes energy. This paper focuses on this tradeoff between preprocessing, pre-filtering and preselecting of sensor data on one hand, and uploading of unprocessed and unfiltered raw data on the other hand, for the special case of protecting vineyards from starlings. The paper proposes a two-phase decision mechanism based on machine learning: the less complex first phase is executed on the microcontroller of the sensor module, while the more complex, more accurate second phase is performed in the cloud. Individual noise sensors monitor the environment, and try to detect starling songs, using a simple, SVM-based classification. These sensors are grouped into clusters, through a mechanism similar to the well-known LEACH protocol, and signal to the current cluster-head the likelihood of starling presence. If several alerts are received to justify further investigation, the cluster-head asks the node with highest starling detection likelihood to upload a one second sound sample to the cloud. There, the more complex and more accurate second phase sound matching is performed, and the actuators deployed in the field are remotely triggered, if needed.

Smith and Smitherson’s Theatre of the Absurd

Smith and Smitherson’s Theatre of the Absurd