Search Results (14)

Background: Sounds that cause disturbances and perturbations to the vestibular (inner ear organ responses) and visual (acute oculomotor responses) systems can impact postural stability. The purpose of this study was to assess the impact of different types of sounds and noises on both static and dynamic PS. Methods: A total of 20 participants (12 females and 8 males; age: 21.35 ± 1.79 years; height: 170.7 ± 9.3 cm; mass: 66.725 ± 14.1 kg) were tested using the limits of stability (LOS) test on the BTrackS™ balance plate and a Timed Up and Go (TUG) test, when exposed to four different sounds and occupational noises [construction noise (CN), white noise (WN), sirens (SRs), and nature sounds (NAs)] in a randomized order with a no sounds (NSs) control performed initially (intensity range of 70–80 dB). The center of pressure (COP) total sway area (cm²) from the LOS and the time to completion of the TUG (seconds) were analyzed using a one-way repeated measures of analysis of variance at an alpha level of 0.05. Results: The observations demonstrated significant differences between the sounds and noises for the TUG (p < 0.001) but not for the LOS test (p = 0.406). Pairwise comparisons for the significant main effect for the TUG revealed that NSs demonstrated significantly slower time to completion compared to CN, WN, and SRs but not NAs. Conclusions: The findings suggest that the different sounds and noises did not impact static PS during the LOS test, which involved the voluntary excursion of the COP while maintaining the same base of support (BOS). However, during dynamic PS with a changing BOS while walking in the TUG, exposure to CN, SRs, and WN demonstrated a faster completion time than NSs or NAs. This finding may be attributed to the anxiety induced by the noise immersion and perception of sounds, compared to calm NAs and no sounds. The findings can aid in better understanding the impact of different occupational noises on PS and emphasize the need for better noise protection and reduction in loud work environments. Full article

Sound-based early fault detection for vehicles is a critical yet underexplored area, particularly within Intelligent Transportation Systems (ITSs) for smart cities. Despite the clear necessity for sound-based diagnostic systems, the scarcity of specialized publicly available datasets presents a major challenge. This study addresses this gap by contributing in multiple dimensions. Firstly, it emphasizes the significance of sound-based diagnostics for real-time detection of faults through analyzing sounds directly generated by vehicles, such as engine or brake noises, and the classification of external emergency sounds, like sirens, relevant to vehicle safety. Secondly, this paper introduces a novel dataset encompassing vehicle fault sounds, emergency sirens, and environmental noises specifically curated to address the absence of such specialized datasets. A comprehensive framework is proposed, combining audio preprocessing, feature extraction (via Mel Spectrograms, MFCCs, and Chromatograms), and classification using 11 models. Evaluations using both compact (52 features) and expanded (126 features) representations show that several classes (e.g., Engine Misfire, Fuel Pump Cartridge Fault, Radiator Fan Failure) achieve near-perfect accuracy, though acoustically similar classes like Universal Joint Failure, Knocking, and Pre-ignition Problem remain challenging. Logistic Regression yielded the highest accuracy of 86.5% for the vehicle fault dataset (DB1) using compact features, while neural networks performed best for datasets DB2 and DB3, achieving 88.4% and 85.5%, respectively. In the second scenario, a Bayesian-Optimized Weighted Soft Voting with Feature Selection (BOWSVFS) approach is proposed, significantly enhancing accuracy to 91.04% for DB1, 88.85% for DB2, and 86.85% for DB3. These results highlight the effectiveness of the proposed methods in addressing key ITS limitations and enhancing accessibility for individuals with disabilities through auditory-based vehicle diagnostics and emergency recognition systems. Full article

This work presents the design and implementation of an emergency sound detection and localization system, specifically for sirens and horns, aimed at enhancing road safety in automotive environments. The system integrates specialized hardware and advanced artificial intelligence algorithms to function effectively in complex acoustic conditions, such as urban traffic and environmental noise. It introduces an aerodynamic structure designed to mitigate wind noise and vibrations in microphones, ensuring high-quality audio capture. In terms of analysis through artificial intelligence, the system utilizes transformer-based architecture and convolutional neural networks (such as residual networks and U-NET) to detect, localize, clean, and analyze nearby sounds. Additionally, it operates in real-time through sliding windows, providing the driver with accurate visual information about the direction, proximity, and trajectory of the emergency sound. Experimental results demonstrate high accuracy in both controlled and real-world conditions, with a detection accuracy of 98.86% for simulated data and 97.5% for real-world measurements, and localization with an average error of 5.12° in simulations and 10.30° in real-world measurements. These results highlight the effectiveness of the proposed approach for integration into driver assistance systems and its potential to improve road safety. Full article

Acoustic perception of the automotive environment has the potential to advance driving potentials with enhanced safety. The challenge arises when these acoustic perception systems need to perform under resource and power constraints on edge devices. Neuromorphic computing has introduced spiking neural networks in the context of ultra-low power sensory edge devices. Spiking architectures leverage biological plausibility to achieve computational capabilities, accurate performance, and great compatibility with neuromorphic hardware. In this work, we explore the depths of spiking neurons and feature components with the acoustic scene analysis task for siren sounds. This research work aims to address the qualitative analysis of sliding windows’ variation on the feature extraction front of the preprocessing pipeline. Optimization of the parameters to exploit the feature extraction stage facilitates the advancement of the performance of the acoustics anomaly detection task. We exploit the parameters for mel spectrogram features and FFT calculations, prone to be suitable for computations in hardware. We conduct experiments with different window sizes and the overlapping ratio within the windows. We present our results for performance measures like accuracy and onset latency to provide an insight on the choice of optimal window. The non-trivial motivation of this research is to understand the effect of encoding behavior of spiking neurons with different windows. We further investigate the heterogeneous nature of membrane and synaptic time constants and their impact on the accuracy of anomaly detection. On a large scale audio dataset comprising of siren sounds and road traffic noises, we obtain accurate predictions of siren sounds using a recurrent spiking neural network. The baseline dataset comprising siren and noise sequences is enriched with a bird dataset to evaluate the model with unseen samples. Full article

This study presents a novel approach to emergency vehicle classification that leverages a comprehensive set of informative audio features to distinguish between ambulance sirens, fire truck sirens, and traffic noise. A unique contribution lies in combining time domain features, including root mean square (RMS) and zero-crossing rate, to capture the temporal characteristics, like signal energy changes, with frequency domain features derived from short-time Fourier transform (STFT). These include spectral centroid, spectral bandwidth, and spectral roll-off, providing insights into the sound’s frequency content for differentiating siren patterns from traffic noise. Additionally, Mel-frequency cepstral coefficients (MFCCs) are incorporated to capture the human-like auditory perception of the spectral information. This combination captures both temporal and spectral characteristics of the audio signals, enhancing the model’s ability to discriminate between emergency vehicles and traffic noise compared to using features from a single domain. A significant contribution of this study is the integration of data augmentation techniques that replicate real-world conditions, including the Doppler effect and noise environment considerations. This study further investigates the effectiveness of different machine learning algorithms applied to the extracted features, performing a comparative analysis to determine the most effective classifier for this task. This analysis reveals that the support vector machine (SVM) achieves the highest accuracy of 99.5%, followed by random forest (RF) and k-nearest neighbors (KNNs) at 98.5%, while AdaBoost lags at 96.0% and long short-term memory (LSTM) has an accuracy of 93%. We also demonstrate the effectiveness of a stacked ensemble classifier, and utilizing these base learners achieves an accuracy of 99.5%. Furthermore, this study conducted leave-one-out cross-validation (LOOCV) to validate the results, with SVM and RF achieving accuracies of 98.5%, followed by KNN and AdaBoost, which are 97.0% and 90.5%. These findings indicate the superior performance of advanced ML techniques in emergency vehicle classification. Full article

Emergency vehicle detection plays a critical role in ensuring timely responses and reducing accidents in modern urban environments. However, traditional methods that rely solely on visual cues face challenges, particularly in adverse conditions. The objective of this research is to enhance emergency vehicle detection by leveraging the synergies between acoustic and visual information. By incorporating advanced deep learning techniques for both acoustic and visual data, our aim is to significantly improve the accuracy and response times. To achieve this goal, we developed an attention-based temporal spectrum network (ATSN) with an attention mechanism specifically designed for ambulance siren sound detection. In parallel, we enhanced visual detection tasks by implementing a Multi-Level Spatial Fusion YOLO (MLSF-YOLO) architecture. To combine the acoustic and visual information effectively, we employed a stacking ensemble learning technique, creating a robust framework for emergency vehicle detection. This approach capitalizes on the strengths of both modalities, allowing for a comprehensive analysis that surpasses existing methods. Through our research, we achieved remarkable results, including a misdetection rate of only 3.81% and an accuracy of 96.19% when applied to visual data containing emergency vehicles. These findings represent significant progress in real-world applications, demonstrating the effectiveness of our approach in improving emergency vehicle detection systems. Full article

The article is devoted to the musical context of the works of James Joyce and Vladimir Nabokov. Joyce’s Ulysses, one of the most important literary texts of the twentieth century, is filled with musical allusions and various musical techniques. The chapter “Sirens” is the most interesting in this context as it features a “musical” form and contains a large number of musical quotations. The myth of the singing sirens, recreated by Joyce in images and characters from the modern world, encapsulates the idea of erotic seduction, bringing threat and doom to the seduced. Joyce offers a new version of the sea world filled with music, creating a system of musical leitmotifs and lexical patterns within the text. Developing the themes of temptation, the danger that temptation entails, doom, uniting with the vital forces of the world, and loneliness, Joyce in “Sirens” reveals the semantics of music, showing the specific nature of its effect on listeners. Vladimir Nabokov, who praised Ulysses and devoted a lecture to “Sirens”, is much less musical than Joyce. However, he, like Joyce, also refers to the images of singing sirens and the accompanying images of the aquatic world. One of the central, meaning-making signs in his work is the “Sirin complex”, his pseudonym. This sign, which refers to a large number of pretexts, refers in particular to the lilac (siren’) and to the mythological “musical” sirens. As in Joyce’s work, sirens are present in his texts as mermaids and naiads, or as figures of seducers who fulfil their function and bring doom. Joyce and Nabokov are also united by the presence of recurrent leitmotifs, lexical patterns, and the presence of auditory impressions in their text that are evoked by the sound of the everyday world. Full article

Wearable assistant devices play an important role in daily life for people with disabilities. Those who have hearing impairments may face dangers while walking or driving on the road. The major danger is their inability to hear warning sounds from cars or ambulances. Thus, the aim of this study is to develop a wearable assistant device with edge computing, allowing the hearing impaired to recognize the warning sounds from vehicles on the road. An EfficientNet-based, fuzzy rank-based ensemble model was proposed to classify seven audio sounds, and it was embedded in an Arduino Nano 33 BLE Sense development board. The audio files were obtained from the CREMA-D dataset and the Large-Scale Audio dataset of emergency vehicle sirens on the road, with a total number of 8756 files. The seven audio sounds included four vocalizations and three sirens. The audio signal was converted into a spectrogram by using the short-time Fourier transform for feature extraction. When one of the three sirens was detected, the wearable assistant device presented alarms by vibrating and displaying messages on the OLED panel. The performances of the EfficientNet-based, fuzzy rank-based ensemble model in offline computing achieved an accuracy of 97.1%, precision of 97.79%, sensitivity of 96.8%, and specificity of 97.04%. In edge computing, the results comprised an accuracy of 95.2%, precision of 93.2%, sensitivity of 95.3%, and specificity of 95.1%. Thus, the proposed wearable assistant device has the potential benefit of helping the hearing impaired to avoid traffic accidents. Full article

It is a well-established practice to build a robust system for sound event detection by training supervised deep learning models on large datasets, but audio data collection and labeling are often challenging and require large amounts of effort. This paper proposes a workflow based on few-shot metric learning for emergency siren detection performed in steps: prototypical networks are trained on publicly available sources or synthetic data in multiple combinations, and at inference time, the best knowledge learned in associating a sound with its class representation is transferred to identify ambulance sirens, given only a few instances for the prototype computation. Performance is evaluated on siren recordings acquired by sensors inside and outside the cabin of an equipped car, investigating the contribution of filtering techniques for background noise reduction. The results show the effectiveness of the proposed approach, achieving AUPRC scores equal to 0.86 and 0.91 in unfiltered and filtered conditions, respectively, outperforming a convolutional baseline model with and without fine-tuning for domain adaptation. Extensive experiments conducted on several recording sensor placements prove that few-shot learning is a reliable technique even in real-world scenarios and gives valuable insights for developing an in-car emergency vehicle detection system. Full article

Germany carried out a nationwide “Alert Day” in 2020 to test its civil alarm systems. The test revealed some problems. Heterogeneous development structures and topography can be limiting factors for sound propagation. In consequence, sirens could be heard inadequately, depending on their location. Furthermore, the reason of warning remains unknown to the public. In terms of civil protection, warnings with the code of behavior by general available media is desired. Smart sirens can transmit additional spoken information and be installed on already-existing streetlights. In this study, we analyze how smart sirens could lead to an improved civil protection. Exemplarily, a detailed analysis is made for a different structured rural area, Dansenberg in Germany, whereas the influence of local conditions on the sound propagation is considered. We analyzed with the software CadnaA—a software for calculation, assessment and prediction of environmental sound—how the location and number of smart sirens can be optimized in order to produce a full coverage of the study area. We modeled the coverage in different scenarios and compared four scenarios: (a) current situation with two E57 type sirens; (b) replacing the existing sirens with two high-performance sirens; (c) one high-performance siren at the more central point; and (d) optimized network of smart sirens of the type Telegrafia Bono. The aim was to achieve a full coverage with a minimum of warning sirens. We could show that the current situation with two E57 type sirens fails to reach out to the whole population whereas the optimized network of smart sirens results in a better coverage. Therefore, a reconsideration of the existing warning system of civil protection with smart sirens could result in a better coverage and improved information of warning. Full article

Due to differences in cognitive ability and physiological development, the evacuation characteristics of children are different from those of adults. This study proposes a novel method of using wearable sensors to collect data (e.g., electrodermal activity, EDA; heart rate variability, HRV) on children’s physiological responses, and to continuously and quantitatively evaluate the effects of different types of alarm sounds during the evacuation of children. In order to determine the optimum alarm for children, an on-site experiment was conducted in a kindergarten to collect physiological data for responses to different types of alarm sounds during the evacuation of 42 children of different ages. The results showed that: (1) The alarm sounds led to changes in physiological indicators of children aged 3–6 years, and the effects of different types of alarm sounds on EDA and HRV activities were significantly different (p < 0.05). Skin conductance (SC), skin conductance tonic (SCT) and skin conductance level (SCL) can be used as the main indicators for analysing EDA of children in this experiment (p < 0.05), and the indicators of ultralow frequency (ULF) and very low frequency (VLF) for HRV were not affected by the type of alarm sounds (p > 0.05). (2) Unlike adults, kindergarten children were more susceptible to the warning siren. The combined voice and warning alarm had optimal effects in stimulating children to perceive risk. (3) For children aged 3–6 years, gender had a significant impact on children’s reception to evacuation sound signals (p < 0.05): Girls are more sensitive than boys in receiving evacuation sound signals, similar to findings of studies of risk perception of adult males and females. In addition, the higher the age, the greater the sensitivity to evacuation sound signals, which accords with results of previous studies on the evacuation dynamics of children. Full article

Firefighters are susceptible to auditory dysfunction due to long-term exposure to noise from sirens, air horns, equipment, and tools used in forcible entry, ventilation, and extrication. In addition, they are exposed to ototoxic chemicals, particularly, during overhaul operations. Studies indicate that 40% of firefighters have hearing loss in the noise-sensitive frequencies of 4 and 6 kHz. Noise-induced hearing loss (NIHL) is often accompanied by tinnitus, which is characterized by ringing noise in the ears. The presence of phantom sounds can adversely affect the performance of firefighters. However, there has been limited research conducted on the prevalence of tinnitus in firefighters. We enrolled firefighters from Michigan, with at least 5 years of continuous service. The hearing handicap inventory for adults (HHIA) was used to determine the difficulty in hearing perceived by the firefighters and the tinnitus functional index (TFI) was used to determine the severity of tinnitus. Self-perceived hearing handicap was reported by 36% of the participants, while tinnitus was reported by 48% of the participants. The TFI survey indicated that 31% perceived tinnitus as a problem. More importantly, self-perceived hearing handicap was significantly associated with the incidence of tinnitus in firefighters, suggesting a potential link between occupational exposure to ototraumatic agents and tinnitus in firefighters. Full article

This essay explores Joyce’s attempt, in “Sirens”, to give articulation to the sounds made by objects and nonhuman beings, with the ultimate goal of destabilizing the boundary separating the human voice (and other forms of human expression) from nonhuman sound. The episode itself can be read as a catalogue of sounds, nonhuman and human, that interact with one another in the absence of a qualitative standard of judgment that would separate the human voice from nonhuman sound, music from “noise”, or conceptual language from sonic expression. Human characters in the episode become what Vike Martina Plock has called “soundboards”, or resonating bodies through which the sounds of their material environment achieve expression. Additionally, human bodies are fragmented metonymically into their sounding body “parts” detached from the unity of the human subject, which allows for new forms of sonorous collaboration between sounding objects and sounding body parts. Nonhuman sounds persist in contrapuntal relation with the voices and sounds of the human characters (and their sounding body parts), a phenomenon which forces us to expand our conception of the fugal form of the episode to include nonhuman entities as collaborators, or “voices”, within it. In this way, “Sirens” asks us to consider sound, and by extension music, not simply as the purely intentional product of a human consciousness, but also as a collective composition between human bodies (and body parts) and the sonic materials of their environment. Full article

A system based on mechanical resonant filters is proposed that can be used for the detection of acoustical signals the frequency components of which vary according to specific periodic patterns. Usually, signals of this category produced by the siren of an emergency vehicle. The device essentially implements a mechanical narrow filter bank that covers the frequency range of a typical siren sound. Signal detection is obtained by measuring the time delay between successive activation of the filters of the bank. The whole analysis reveals how a set of simple, low-cost mechanical resonant filters can replace an electronic analog or digital system for the implementation of a filter bank. Moreover, a scaling down procedure is proposed so that a microsystem may be developed. Full article