Search Results (47)

Deep learning has emerged as a powerful technique for speech enhancement, particularly in security systems where audio signals are often degraded by non-stationary noise. Traditional signal processing methods struggle in such conditions, making it difficult to detect critical sounds like gunshots, alarms, and unauthorized speech. This study investigates a hybrid deep learning framework that combines Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Generative Adversarial Networks (GANs) to enhance speech quality and improve sound classification accuracy in noisy security environments. The proposed model is trained and validated using real-world datasets containing diverse noise distortions, including VoxCeleb for benchmarking speech enhancement and UrbanSound8K and ESC-50 for sound classification. Performance is evaluated using industry-standard metrics such as Perceptual Evaluation of Speech Quality (PESQ), Short-Time Objective Intelligibility (STOI), and Signal-to-Noise Ratio (SNR). The architecture includes multi-layered neural networks, residual connections, and dropout regularization to ensure robustness and generalizability. Additionally, the paper addresses key challenges in deploying deep learning models for security applications, such as computational complexity, latency, and vulnerability to adversarial attacks. Experimental results demonstrate that the proposed DNN + GAN-based approach significantly improves speech intelligibility and classification performance in high-interference scenarios, offering a scalable solution for enhancing the reliability of audio-based security systems. Full article

Acoustic scene classification aims to recognize the scenes corresponding to sound signals in the environment, but audio differences from different cities and devices can affect the model’s accuracy. In this paper, a time–frequency–wavelet fusion network is proposed to improve model performance by focusing on three dimensions: the time dimension of the spectrogram, the frequency dimension, and the high- and low-frequency information extracted by a wavelet transform through a time–frequency–wavelet module. Multidimensional information was fused through the gated temporal–spatial attention unit, and the visual state space module was introduced to enhance the contextual modeling capability of audio sequences. In addition, Kolmogorov–Arnold network layers were used in place of multilayer perceptrons in the classifier part. The experimental results show that the proposed method achieves a 56.16% average accuracy on the TAU Urban Acoustic Scenes 2022 mobile development dataset, which is an improvement of 6.53% compared to the official baseline system. This performance improvement demonstrates the effectiveness of the model in complex scenarios. In addition, the accuracy of the proposed method on the UrbanSound8K dataset reached 97.60%, which is significantly better than the existing methods, further verifying the generalization ability of the proposed model in the acoustic scene classification task. Full article

While open-set recognition algorithms have been extensively explored in computer vision, their application to environmental sound analysis remains understudied. To address this gap, this study investigates how to effectively recognize unknown sound categories in real-world environments by proposing a novel Kernel Density Estimation-based Generative Adversarial Network (KDE-GAN) for data augmentation combined with Attractor–Reciprocal Point Learning for open-set classification. Specifically, our approach addresses three key challenges: (1) How to generate boundary-aware synthetic samples for robust open-set training: A closed-set classifier’s pre-logit layer outputs are fed into the KDE-GAN, which synthesizes samples mapped to the logit layer using the classifier’s original weights. Kernel Density Estimation then enforces Density Loss and Offset Loss to ensure these samples align with class boundaries. (2) How to optimize feature space organization: The closed-set classifier is constrained by an Attractor–Reciprocal Point joint loss, maintaining intra-class compactness while pushing unknown samples toward low-density regions. (3) How to evaluate performance in highly open scenarios: We validate the method using UrbanSound8K, AudioEventDataset, and TUT Acoustic Scenes 2017 as closed sets, with ESC-50 categories as open-set samples, achieving AUROC/OSCR scores of 0.9251/0.8743, 0.7921/0.7135, and 0.8209/0.6262, respectively. The findings demonstrate the potential of this framework to enhance environmental sound monitoring systems, particularly in applications requiring adaptability to unseen acoustic events (e.g., urban noise surveillance or wildlife monitoring). Full article

Precision livestock farming technologies support health monitoring on farms, yet few studies have evaluated their effectiveness under field conditions using reliable gold standards. This study evaluated a commercially available technology for detecting cough sounds in pigs on a commercial farm. Audio was recorded over six days using 16 microphones across two pig barns. A total of 1110 cough sounds were labelled by an on-site observer using a cough induction methodology, and 8938 other sounds from farm recordings and open-source datasets (ESC-50, UrbanSound8K, and AudioSet) were labelled. A hybrid deep learning model combining Convolutional Neural Networks and Recurrent Neural Networks was trained and evaluated using these labels. A total of 34 audio features were extracted from 1 s segments, including validated descriptors (e.g., MFCC), unverified external features, and proprietary features. Features were evaluated through 10-fold cross-validation based on classification performance and runtime, resulting in eight final features. The final model showed high performance (recall = 98.6%, specificity = 99.7%, precision = 98.8%, accuracy = 99.6%, F1-score = 98.6%). The technology tested was shown to be efficient for monitoring cough sounds in a commercial swine production facility. It is recommended to test the technology in other environments to evaluate the effectiveness in different farm settings. Full article

Urban green spaces are critical yet understudied areas where anthropogenic and biological sounds interact. This study investigates how vegetation structure mediates the acoustic partitioning of urban soundscapes and informs sustainable forestry management. Through the principal component analysis (PCA) of 1–11 kHz frequency bands, we identified anthropogenic sounds (1–2 kHz) and biological sounds (2–11 kHz). Within bio-acoustic communities, PCA further revealed three positively correlated sub-clusters (2–4 kHz, 5–6 kHz, and 6–11 kHz), suggesting cooperative niche partitioning among avian, amphibian, and insect vocalizations. Linear mixed models highlighted vegetation’s dual role: mature tree stands (explaining 19.9% variance) and complex vertical structures (leaf-height diversity: 12.2%) significantly enhanced biological soundscapes (R²m = 0.43) while suppressing anthropogenic noise through canopy stratification (32.3% variance explained). Based on our findings, we suggest that an acoustic data-driven framework—comprising (1) the preservation of mature stands with multi-layered canopies to enhance bioacoustic resilience, (2) strategic planting of mid-story vegetation to disrupt low-frequency noise propagation, and (3) real-time soundscape monitoring to balance biophony and anthropophony allocation—can contribute to promoting sustainable urban forestry management. Full article

Audio tagging, as a fundamental task in acoustic signal processing, has demonstrated significant advances and broad applications in recent years. Spiking Neural Networks (SNNs), inspired by biological neural systems, exploit event-driven computing paradigms and temporal information processing, enabling superior energy efficiency. Despite the increasing adoption of SNNs, the potential of event-driven encoding mechanisms for audio tagging remains largely unexplored. This work presents a pioneering investigation into event-driven encoding strategies for SNN-based audio tagging. We propose the SATRN (Spiking Audio Tagging Robust Network), a novel architecture that integrates temporal–spatial attention mechanisms with membrane potential residual connections. The network employs a dual-stream structure combining global feature fusion and local feature extraction through inverted bottleneck blocks, specifically designed for efficient audio processing. Furthermore, we introduce an event-based encoding approach that enhances the resilience of Spiking Neural Networks to disturbances while maintaining performance. Our experimental results on the Urbansound8k and FSD50K datasets demonstrate that the SATRN achieves comparable performance to traditional Convolutional Neural Networks (CNNs) while requiring significantly less computation time and showing superior robustness against noise perturbations, making it particularly suitable for edge computing scenarios and real-time audio processing applications. Full article

Rapid urbanization presents significant challenges in energy consumption, noise control, and environmental sustainability. Smart cities aim to address these issues by leveraging information technologies to enhance operational efficiency and urban liveability. In this context, urban sound recognition supports environmental monitoring and public safety. This study provides a comparative evaluation of three machine learning models—convolutional neural networks (CNNs), long short-term memory (LSTM), and dense neural networks (Dense)—for classifying urban sounds. The analysis used the UrbanSound8K dataset, a static dataset designed for environmental sound classification, with mel-frequency cepstral coefficients (MFCCs) applied to extract core sound features. The models were tested in a fog computing architecture on AWS to simulate a smart city environment, chosen for its potential to reduce latency and optimize bandwidth for future real-time sound-recognition applications. Although real-time data were not used, the simulated setup effectively assessed model performance under conditions relevant to smart city applications. According to macro and weighted F1-score metrics, the CNN model achieved the highest accuracy at 90%, followed by the Dense model at 84% and the LSTM model at 81%, with the LSTM model showing limitations in distinguishing overlapping sound categories. These simulations demonstrated the framework’s capacity to enable efficient urban sound recognition within a fog-enabled architecture, underscoring its potential for real-time environmental monitoring and public safety applications. Full article

The potential of electric vehicles (EVs) to support the decarbonization of the transportation sector, crucial for meeting greenhouse gas reduction targets under the Paris Agreement, is obvious. Despite their advantages, the adoption of electric vehicles faces limitations, particularly those related to battery range and charging times, which significantly impact the time needed for a trip compared to their combustion engine counterparts. However, recent improvements in fast charging technology have enhanced these aspects, making EVs more suitable for both daily and long-distance trips. EVs can now deal with long trips, with travel times only slightly longer than those of internal combustion engine (ICE) vehicles. Fast charging capabilities and infrastructure, such as 350 kW chargers, are essential for making EV travel times comparable to ICE vehicles, with brief stops every 2–3 h. Additionally, EVs help reduce noise pollution in urban areas, especially in noise-saturated environments, contributing to an overall decrease in urban sound levels. However, this research highlights a downside of DC (Direct Current) fast charging stations: high-frequency noise emissions during fast charging, which can disturb nearby residents, especially in urban and residential areas. This noise, a result of the growing fast charging infrastructure, has led to complaints and even operational restrictions for some charging stations. Noise-related disturbances are a significant urban issue. The World Health Organization identifies noise as a key contributor to health burdens in Europe, even when noise annoyance is subjective, influenced by individual factors like sensitivity, genetics, and lifestyle, as well as by the specific environment. This paper analyzes the sound emission of a broad sample of DC fast charging stations from leading EU market brands. The goal is to provide tools that assist manufacturers, installers, and operators of rapid charging stations in mitigating the aforementioned sound emissions in order to align these infrastructures with Sustainable Development Goals 3 and 11 adopted by all United Nations Member States in 2015. Full article

With advancements in the Internet of Things (IoT), diverse and high-resolution data sources, such as environmental sensors and user-generated inputs from mobile devices, have become available to model and estimate citizens’ acoustic comfort in urban environments. These IoT-enabled data sources offer scalable insights in real time into both objective parameters (e.g., noise levels and environmental conditions) and subjective perceptions (e.g., personal comfort and soundscape experiences), which were previously challenging to capture comprehensively by using traditional methods. Despite this, there remains a lack of a clear framework explicitly presenting the role of these diverse inputs in determining acoustic comfort. This paper contributes by (1) exploring the relationship between attributes governing the physical aspect of the built environment (sensory data) and the end-users’ characteristics/inputs/sensations (such as their acoustic comfort level) and how these attributes can correlate/connect; (2) developing a CityGML-based framework that leverages semantic 3D city models to integrate and represent both objective sensory data and subjective social inputs, enhancing data-driven decision making at the city level; and (3) introducing a novel approach to crowdsourcing citizen inputs to assess perceived acoustic comfort indicators, which inform predictive modeling efforts. Our solution is based on CityGML’s capacity to store and explain 3D city-related shapes with their semantic characteristics, which are essential for city-level operations such as spatial data mining and thematic queries. To do so, a crowdsourcing method was used, and 20 perceptive indicators were identified from the existing literature to evaluate people’s perceived acoustic attributes and types of sound sources and their relations to the perceived soundscape comfort. Three regression models—K-Nearest Neighbor (KNN), Support Vector Regression (SVR), and XGBoost—were trained on the collected data to predict acoustic comfort at bus stops in Montréal based on physical and psychological attributes of travellers. In the best-performing scenario, which incorporated psychological attributes and measured noise levels, the models achieved a normalized mean squared error (NMSE) as low as 0.0181, a mean absolute error (MAE) of 0.0890, and a root mean square error (RMSE) of 0.1349. These findings highlight the effectiveness of integrating subjective and objective data sources to accurately predict acoustic comfort in urban environments. Full article

The majority of sound events that occur in everyday life, like those caused by animals or household devices, can be included in the environmental sound family. This audio category has not been researched as much as music or speech recognition. One main bottleneck in the design of environmental data-driven monitoring automation is the lack of sufficient data representing each of a wide range of categories. In the context of audio data, an important method to increase the available data is the process of the augmentation of existing datasets. In this study, some of the most widespread time domain data augmentation techniques are studied, along with their effects on the recognition of environmental sounds, through the UrbanSound8K dataset, which consists of ten classes. The confusion matrix and the metrics that can be calculated based on the matrix were used to examine the effect of the augmentation. Also, to address the difficulty that arises when large datasets are augmented, a web-based data augmentation application was created. To evaluate the performance of the data augmentation techniques, a convolutional neural network architecture trained on the original set was used. Moreover, four time domain augmentation techniques were used. Although the parameters of the techniques applied were chosen conservatively, they helped the model to better cluster the data, especially in the four classes in which confusion was high in the initial classification. Furthermore, a web application is presented in which the user can upload their own data and apply these data augmentation techniques to both the audio extract and its time frequency representation, the spectrogram. Full article

Video surveillance is an effective tool for traffic management and safety, but it may face challenges in extreme weather, low visibility, areas outside the monitoring field of view, or during nighttime conditions. Therefore, abnormal sound detection is used in traffic management and safety as an auxiliary tool to complement video surveillance. In this paper, a novel lightweight method for abnormal sound detection based on 1D CNN and Multi-Head Self-Attention Mechanism on the embedded system is proposed, which is named HADNet. First, 1D CNN is employed for local feature extraction, which minimizes information loss from the audio signal during time-frequency conversion and reduces computational complexity. Second, the proposed block based on Multi-Head Self-Attention Mechanism not only effectively mitigates the issue of disappearing gradients, but also enhances detection accuracy. Finally, the joint loss function is employed to detect abnormal audio. This choice helps address issues related to unbalanced training data and class overlap, thereby improving model performance on imbalanced datasets. The proposed HADNet method was evaluated on the MIVIA Road Events and UrbanSound8K datasets. The results demonstrate that the proposed method for abnormal audio detection on embedded systems achieves high accuracy of 99.6% and an efficient detection time of 0.06 s. This approach proves to be robust and suitable for practical applications in traffic management and safety. By addressing the challenges posed by traditional video surveillance methods, HADNet offers a valuable and complementary solution for enhancing safety measures in diverse traffic conditions. Full article

In urban environments, noise significantly impacts daily life and presents challenges for Environmental Sound Classification (ESC). The structural influence of urban noise on audio signals complicates feature extraction and audio classification for environmental sound classification methods. To address these challenges, this paper proposes a Contrastive Learning-based Audio Spectrogram Transformer (CL-Transformer) that incorporates a Patch-Mix mechanism and adaptive contrastive learning strategies while simultaneously improving and utilizing adaptive data augmentation techniques for model training. Firstly, a combination of data augmentation techniques is introduced to enrich environmental sounds. Then, the Patch-Mix feature fusion scheme randomly mixes patches of the enhanced and noisy spectrograms during the Transformer’s patch embedding. Furthermore, a novel contrastive learning scheme is introduced to quantify loss and improve model performance, synergizing well with the Transformer model. Finally, experiments on the ESC-50 and UrbanSound8K public datasets achieved accuracies of 97.75% and 92.95%, respectively. To simulate the impact of noise in real urban environments, the model is evaluated using the UrbanSound8K dataset with added background noise at different signal-to-noise ratios (SNR). Experimental results demonstrate that the proposed framework performs well in noisy environments. Full article

Birds play a pivotal role in ecosystem and biodiversity research, and accurate bird identification contributes to the monitoring of biodiversity, understanding of ecosystem functionality, and development of effective conservation strategies. Current methods for bird sound recognition often involve processing bird songs into various acoustic features or fusion features for identification, which can result in information loss and complicate the recognition process. At the same time, the recognition method based on raw bird audio has not received widespread attention. Therefore, this study proposes a bird sound recognition method that utilizes multiple one-dimensional convolutional neural networks to directly learn feature representations from raw audio data, simplifying the feature extraction process. We also apply positional embedding convolution and multiple Transformer modules to enhance feature processing and improve accuracy. Additionally, we introduce a trainable weight array to control the importance of each Transformer module for better generalization of the model. Experimental results demonstrate our model’s effectiveness, with an accuracy rate of 99.58% for the public dataset Birds_data, as well as 98.77% for the Birdsonund1 dataset, and 99.03% for the UrbanSound8K environment sound dataset. Full article

With the rapid industrialization utilizing multi-rotor drones in recent years, an increase in urban flights is expected in the near future. This may potentially result in noise pollution due to the operation of drones. This study investigates the near- and far-field acoustic characteristics of low-noise propellers inspired by Gurney flaps. In addition, we examine the impact of these low-noise propellers on the sound source localization performance of drones equipped with a microphone array, which are expected to be used for rescuing people in disasters. Results from in-flight noise measurements indicate significant noise reduction mainly in frequency bands above 1 kHz in both the near- and far-field. An improvement in the success rate of sound source localization with low-noise propellers was also observed. However, the influence of the position of the microphone array with respect to the propellers is more pronounced than that of propeller shape manipulation, suggesting the importance of considering the positional relationships. Computational fluid dynamics analysis of the flow field around the propellers suggests potential mechanisms for noise reduction in the developed low-noise propellers. The results obtained in this study hold potential for contributing to the development of integrated drones aimed at reducing noise and improving sound source localization performance. Full article

The combination of deep-learning and IoT plays a significant role in modern smart solutions, providing the capability of handling task-specific real-time offline operations with improved accuracy and minimised resource consumption. This study provides a novel hardware-aware neural architecture search approach called ESC-NAS, to design and develop deep convolutional neural network architectures specifically tailored for handling raw audio inputs in environmental sound classification applications under limited computational resources. The ESC-NAS process consists of a novel cell-based neural architecture search space built with 2D convolution, batch normalization, and max pooling layers, and capable of extracting features from raw audio. A black-box Bayesian optimization search strategy explores the search space and the resulting model architectures are evaluated through hardware simulation. The models obtained from the ESC-NAS process achieved the optimal trade-off between model performance and resource consumption compared to the existing literature. The ESC-NAS models achieved accuracies of 85.78%, 81.25%, 96.25%, and 81.0% for the FSC22, UrbanSound8K, ESC-10, and ESC-50 datasets, respectively, with optimal model sizes and parameter counts for edge deployment. Full article