Horn Sounds Research Articles

Recognition of car horns based on principal component analysis of MEL frequency Cepstral coefficients and support vector machine

With the rapid increase in the number of automobiles, the noise pollution caused by car horns is attracting more attention. In order to accurately identify car horn sounds in traffic noise and strengthen traffic law enforcement, research on car horn sound recognition is becoming increasingly important. In this paper, using Principal Component Analysis (PCA) to optimize and reduce the dimensionality of extracted Mel Frequency Cepstral Coefficients (MFCC), feature vectors are input into four models: Support Vector Machine (SVM), Back Propagation (BP) Neural Network, Extreme Learning Machine (ELM), and Random Forest (RF). These models are utilized to classify and identify car horn sounds from traffic noise. The impact of feature dimensions and Signal-to-noise ratio(SNR) on recognition performance is analyzed. The results show that under this method, the recognition rates of the four models can be increased by increasing the number of Mel filters and feature dimensions in MFCC, which can improve recognition performance, especially when the SNR is lower. The SVM model exhibits the most significant improvement in recognition rate. They achieve the best recognition rates for measured car horn sounds of 98.66 %, 93.98 %, 89.44 %, and 95.12 %, respectively. Experimental results demonstrate that the proposed method has good recognition performance and can be effectively applied to the supervision of car horn usage on actual roads.

Tailored for vehicle horn: A novel sound source capture method

The development of a horn sound capture system, capable of replacing manual control, offers a promising solution for alleviating horn noise. Existing horn sound systems lack localization algorithms that are capable of robustly resisting interference. To address this issue, this paper introduces an innovative horn sound capture system, including hardware and algorithms for sound recognition and localization. The pivotal innovation of the system is the introduction of the Sub-SRP algorithm, an advancement of the steered-response power phase transform (SRP-PHAT). Leveraging the frequency characteristics of horn sounds, it employs a series of filtering and spectral subtraction techniques to effectively filter out non-horn noise sources. In the interference experiment and field test, the Sub-SRP algorithm achieved DOA scores of 0.96 and 0.95, respectively, showing an approximately 10% improvement compared to the existing weighted SRP-PHAT, this improvement is even more pronounced under strong interference, increasing to 17%. This improvement significantly enhances the system’s ability to accurately capture honking vehicles and resist interference. Additionally, the horn sound recognition algorithm achieved accuracy rates of 95.75% and 97.65% in the two experiments, demonstrating the system’s effectiveness. In summary, this study contributes to the advancement of urban noise management and intelligent noise control systems.

Auditory impression of amplitude-modulated vehicle horn sounds and their detectability in noisy environment

Vehicle horn sounds, due to their high sound pressure levels, induce negative psychological reactions in listeners, especially pedestrians. In order to reduce such negative effects, a horn sound with a lower sound pressure level is desired. At the same time, a horn sound should be easily perceived by drivers, considering its use on busy roads. The amplitude-modulated horn sound may help to solve these problems. Therefore, we synthesized amplitude-modulated horn sounds, and conducted psychoacoustical experiments to investigate the relationship between the acoustic characteristics and the perceived quality of these sounds. The results showed that stimuli with shallower modulation depths were less unpleasant than those with deeper modulation depths, and stimuli with modulation frequencies below 40 Hz suppressed auditory unpleasantness more than those with higher modulation frequencies. To confirm their effectiveness for detection in noisy conditions, stimuli with different signal-to-noise ratios were created by combining the amplitude-modulated horn sound and road traffic noise. The amplitude-modulated horn sound in road traffic noise was detected even in conditions where the signal-to-noise ratio was 3 dB lower than when the horn sound was not amplitude-modulated. The results indicate that amplitude-modulated horn sounds have the potential to improve the sound environment around roads.

Crafting the voice of God: ceramic waylla kepa shell horn technology in the Andes

This paper addresses the enchainment of skills and interactions for the production of ceramic shell horns, and the meaning of these musical instruments whose sounds have shaped the ritual soundscapes of the central Andes since the boom in public architecture in the second millennium BC (early Formative Period c. 3800–3300 BP). Linguistic and ethnohistoric reviews shed light on performance practices and meanings at the time of conquest. Contextual analysis of thin sections of ceramic shell horns excavated in Keushu (Yungay, Ancash, Peru) and dated to the Early Intermediate Period and early Middle Horizon (c. 2200–1600 BP) suggests the agency of specialist itinerant potters. Crafting processes are reconstructed by bringing together material analysis (petrography, X-ray tomography, X-ray diffraction), bioarchaeology, studies of instrument organology, and ceramic ethnoarchaeology. Informed by experimental reconstruction distinct modeling techniques are distinguished and crossed with available provenience data to suggest three independently arising traditions or hotspots in northern Ecuador, on the central Andean coast, and in the highlands of northern Peru. The ritual sounds and soundscapes of the latter area are discussed. Like earlier conch horns, ceramic shell horns played a pivotal part in ritual performances that accompanied the development of irrigation-dependent agrarian and pastoral lifeways in the Andes. Enduring symbolic linkages between shell horn sounds, the sea and irrigation water may indeed represent a powerful embodiment of the voice of God.

End-to-End Train Horn Detection for Railway Transit Safety.

The train horn sound is an active audible warning signal used for warning commuters and railway employees of the oncoming train(s), assuring a smooth operation and traffic safety, especially at barrier-free crossings. This work studies deep learning-based approaches to develop a system providing the early detection of train arrival based on the recognition of train horn sounds from the traffic soundscape. A custom dataset of train horn sounds, car horn sounds, and traffic noises is developed to conduct experiments and analysis. We propose a novel two-stream end-to-end CNN model (i.e., THD-RawNet), which combines two approaches of feature extraction from raw audio waveforms, for audio classification in train horn detection (THD). Besides a stream with a sequential one-dimensional CNN (1D-CNN) as in existing sound classification works, we propose to utilize multiple 1D-CNN branches to process raw waves in different temporal resolutions to extract an image-like representation for the 2D-CNN classification part. Our experiment results and comparative analysis have proved the effectiveness of the proposed two-stream network and the method of combining features extracted in multiple temporal resolutions. The THD-RawNet obtained better accuracies and robustness compared to those of baseline models trained on either raw audio or handcrafted features, in which at the input size of one second the network yielded an accuracy of 95.11% for testing data in normal traffic conditions and remained above a 93% accuracy for the considerable noisy condition of-10 dB SNR. The proposed THD system can be integrated into the smart railway crossing systems, private cars, and self-driving cars to improve railway transit safety.

Rancang Bangun Sistem Keamanan Dan Pengendali Jarak Jauh Sepeda Motor Menggunakan Android Berbasis Nodemcu ESP32 dan GPS

Technological developments have penetrated various fields, including motor vehicle safety. The manufacturer's standard locking system is deemed insufficient to protect motorized vehicles from theft. A combination of software and hardware is required to create an additional security system. The purpose of this research is to design and build a motorcycle safety device using IoT-based GPS. The system is designed when a forced vibration occurs in the ignition zone, a warning message is sent via the Blynk application and the horn sounds. To turn on the machine, you can via the widget in the Blynk application, the Contacts button is ON, then press the Machine ON to turn off the machine by pressing the Contacts OFF button in the Blynk application. To detect the location of a smartphone-controlled motorcycle with the Blynk application. The design of this tool uses several components, namely the SW-420 vibration sensor as an engine warning indicator sensor, the Neo6mv2 GPS sensor as a coordinate sensor, using the NodeMCU ESP32 microcontroller to process data and communicate with a WiFi modem and use a relay as a control button to turn on and off the engine, turn on horn. All components require a 5V supply voltage from a 12V motor battery, this voltage is reduced to 5V with the LM2596 module.

Convolutional Neural Networks Using Log Mel-Spectrogram Separation for Audio Event Classification with Unknown Devices

Audio event classification refers to the detection and classification of non-verbal signals, such as dog and horn sounds included in audio data, by a computer. Recently, deep neural network technology has been applied to audio event classification, exhibiting higher performance when compared to existing models. Among them, a convolutional neural network (CNN)-based training method that receives audio in the form of a spectrogram, which is a two-dimensional image, has been widely used. However, audio event classification has poor performance on test data when it is recorded by a device (unknown device) different from that used to record training data (known device). This is because the frequency range emphasized is different for each device used during recording, and the shapes of the resulting spectrograms generated by known devices and those generated by unknown devices differ. In this study, to improve the performance of the event classification system, a CNN based on the log mel-spectrogram separation technique was applied to the event classification system, and the performance of unknown devices was evaluated. The system can classify 16 types of audio signals. It receives audio data at 0.4-s length, and measures the accuracy of test data generated from unknown devices with a model trained via training data generated from known devices. The experiment showed that the performance compared to the baseline exhibited a relative improvement of up to 37.33%, from 63.63% to 73.33% based on Google Pixel, and from 47.42% to 65.12% based on the LG V50.

Evaluation of the Visually Impaired Experience of the Sound Environment in Urban Spaces

Visually impaired people have unique perceptions of and usage requirements for various urban spaces. Therefore, understanding these perceptions can help create reasonable layouts and construct urban infrastructure. This study recruited 26 visually impaired volunteers to evaluate 24 sound environments regarding clarity, comfort, safety, vitality, and depression. This data was collected in seven different types of urban spaces. An independent sample non-parametric test was used to determine the significance of the differences between environmental evaluation results for each evaluation dimension and to summarize the compositions of sound and space elements in the positive and negative influence spaces. The results suggested that visually impaired people (1) feel comfort, safety, and clarity in parks, residential communities, and shopping streets; (2) have negative perceptions of vegetable markets, bus stops, hospitals, and urban departments; (3) feel anxious when traffic sounds, horn sounds, manhole cover sounds, and construction sounds occur; and (4) prefer spaces away from traffic, with fewer and slower vehicles, with a suitable space scale, and moderate crowd density. These results provide a reference for the future design of activity venues (i.e., residential communities, vegetable markets, bus stops, parks, shopping streets, hospitals, and urban functional departments) and the planning of accessibility systems for visually impaired urban residents.

Impressions and interpretations of vehicle horn sounds with acoustic characteristics of speech

In Japan, vehicle horns have been used as a means of communication between drivers, and frequently aroused psychological negative reactions in hearers. If horn sounds have acoustic features of speech, they possibly help communication between drivers, and improve hearers' negative impressions. To investigate such hypotheses, psychoacoustical experiments were conducted using synthesized horn sounds with acoustic characteristics of Japanese speech "abunai", which implies a dangerous situation. Spectral features and temporal envelopes were extracted from the speech stimulus and the similar one with swapped syllables, and were reflected in horn sounds. Two experiments were carried out to examine the effects of acoustic characteristics of horn sounds on the perceived quality and interpretations of the intention behind another driver's horn use. Stimuli with spectral characteristics of the speech and those of swapped syllables were evaluated as being less unpleasant and more safe than the original horn sound. On the other hand, many responses of 'caution' and 'danger' were obtained for the stimulus with spectral characteristics of the speech. Results suggested that the horn sound with spectral characteristics of the speech improved from the original horn sound in the perceived quality, and correctly communicated the intention behind another driver's horn use.

Auditory Alerts and Safety with Simulated Bicycles and Motor Vehicles

Bicycling has become an increasingly popular and environmentally friendly active transportation modality for many commuters across the nation. Consequently, as ridership increases so does the rate of bicycle–motor vehicle crashes, many of which are caused by reduced bicycle visibility and driver inattention. Therefore, one effective solution to improve bicyclist safety may be through the use of an audible bicycle alarm system to alert both the driver and the rider. A study was conducted to determine whether a unique auditory alert would be effective at reducing crash rates and whether a localized alert (i.e., an alert presented from the driver’s perspective) would improve the driver’s responsiveness in avoiding a potential collision. A driving simulator study tested car horn sounds, an experimental bike alert, and no auditory alert in different potential collision scenarios to measure collision rates and other collision avoidance metrics. Findings indicated that the experimental bike alert contributed to fewer relative crashes than the horn sound and no sound on bicycles, motor vehicles were struck more frequently than bicycles, collisions were more likely to occur from the front than the sides, and collisions were more likely for drivers going straight than when making turns. Taken together, the findings suggest that an alarm designed to be specifically compatible with bicycles is more effective than auditory alerts from other sources.

Significance of electronic music

Music is one of the most influential components in the world today. In fact, music plays significant roles in influencing human behavior and practices. Electronic music refers to all types of music played or produced through electronic devices. The twenty-first century is a century of technology whereby everything is done through the use of technology. Technology has brought about electronic devices which are used to play music in the modern world. Electronic music involves various forms and speed. Some forms of electronic music involve house, jungle, techno and trance. Jungle music involves “break” or rap that is mixed and sped up with various sounds. Techno and jungle are almost similar although techno tends to be harder and involves more whistles and horn sounds compared to jungle. However, all these forms of music are produced with the help of electronic devices. In fact, it is impossible to use trumpet to produce house music and thus electronic devices such as computer, turntables, a synthesizer or sampler are very significant in producing electronic music.

Chaotic global analysis of heart rate variability following power spectral adjustments during exposure to traffic noise in healthy adult women

Aim. Previous studies have described the substantial impact of different types of noise on the linear behaviour of heart rate variability (HRV). Yet, there are limited studies about the complexity or nonlinear dynamics of HRV during exposure to traffic noise. Here, we evaluated the complexity of HRV during traffic noise exposure via six power spectra and, when adjusted by the parameters of the Multi-Taper Method (MTM).Material and methods. We analysed 31 healthy female students between 18 and 30 years old. Subjects remained at rest, seated under spontaneous breathing for 20 minutes with an earphone turned off and then the volunteers were exposed to traffic noise through an earphone for a period of 20 minutes. The traffic noise was recorded from a busy urban street and the sound involved car, bus, trucks engineers and horn sounds (71-104 dB).Results. The results stipulate that CFP3 and CFP6 are the best metrics to distinguish the two groups. The most appropriate power spectra were, Welch and MTM. Increasing the DPSS parameter of MTM increased the performance of both CFP3 and CFP6 as mathematical markers. Adaptive was the preferred type for Thomson’s nonlinear combination method.Conclusion. CFP3 with the adaptive option for MTM, and increased DPSS is designated as the best mathematical marker on the basis of five statistical tests.

Acoustic vehicle alerts and sleep disruption: A content analysis of online complaints and inquiries

Research on the effects of traffic noise on sleep focuses on sounds created by vehicles that are traveling, whether in continuous motion on a highway or road or temporarily slowed on a congested street. Most acoustic vehicle alerts are introduced without consideration for their potential to disrupt sleep or affect quality of life. Panic alarm, marketed as a safety feature and standard with most cars, was accepted by regulatory and consumer protection agencies without question or concern for its necessity or its potential to create new noise. Criticism about car alarms, remote lock signals that use horn sounds, panic alarm, and backup beeping in passenger cars is common in everyday discourse but rare within the public health sphere. This study will use content analysis of online complaints posted in public databases, discussion forums, and car owner forums to explore common experiences related to sleep disruption. Focus will be on technologies not used while driving and will not include pedestrian alerts or backup beeping used by commercial or industrial vehicles. The study will include posts by those whose sleep has been affected and by car owners inquiring about methods of turning off a sound source out of concern for a neighbor.

The Effect of Speed Factors and Horn Sound to The RLS 90 Model Reliability on The Visum Program in Predicting Noise of Heterogeneous Traffic

This study aimed to predict the noise generated by heterogeneous traffic using RLS 90 model on the Visum program, evaluating and looking for correction factor. Points of observation were taken at 37 points on the road side at 06.00 - 18.00 and 06.00 - 21.00 with research object are motorcycle, light vehicle and heavy vehicle. The observed data are traffic volume, vehicle speed, number of horn and traffic noise by using Sound Level Meter Tenmars TM-103. The result shows the prediction model of RLS 90 Visum program produces an average noise level value of 69.3 dB with Pearson’s correlation and RMSE of 0.71 and 9.97, the prediction model RLS 90 vehicle correction produces an average noise level value of 77.9 dB with Pearson’s correlation and RMSE of 0.75 and 2.02, whereas the prediction model RLS 90 vehicle and horn correction produces an average noise level value of 79.1 dB with Pearson’s correlation and RMSE of 0.83 and 1.29. So that, prediction model RLS 90 with vehicle and horn correction quite good which has a relationship of Y = 0.71 X + 29.65 to the prediction model RLS 90 with Visum program.

A study on a friendly automobile klaxon production with rhythm

We are always exposed to traffic noise in our lives. Especially in unproven situations, exposure to a sudden sound may result in loss of auditory cells and exposure to retaliatory driving. However, if you do not use horn sounds, you will not be free from traffic accidents when driving. The Clackson is used as a car horn and has a simple mechanical structure, which is easy to use. However, it has a disadvantage that it can not redesign the sound pressure of fluid sound. In this study, the power supply time width of Clackson was adjusted to five (0.01 s, 0.02 s, 0.03s, 0.06 s, and 0.13 s). The result was a sound level of five (80 dB, 85 dB, 90 dB, 100 dB, and 110 dB) sound levels of the Klaxon. The experimental result shows that the maximum sound pressure (pmax = 110 dB) after operating the clackson is tmax. Ps (dB) = 110 (dB)—{10log (ton / (ton + toff)) + 20log (ton / tmax) The preference was evaluated for five types of Clackson sounds of 5 seconds. The MOS evaluation was performed on 100 participants after three times of five kinds of Klaxon sounds. The evaluation items were MOS measurement for risk, sound size, unpleasantness, and stress. As a result of evaluation, when designing various forms of clackson sound, it was quickly felt that it is danger to give a sound rhythm to a horn sound rather than a conventional sound. In particular, if you change the rhythm of the sound of Klaxon, the risk perception becomes faster even though the average sound level is lowered by −20 dB.

Horn Sounds in Transportation Systems and a Cognitive Perspective on the Instant Mood-Condition Disorder

This study was performed on sidewalks that there can secure movement of pedestrians. The basic theme of the research is how pedestrians are influenced by the sudden hearings of horns in the walking moments. In this study on different horns chord samples were randomly presented during simultaneous Electroencephalogram (EEG) recordings to a total of 48 healthy participants aged between 25–65 years; the elicited brain responses were examined. EEG recording with visual stimuli is performed on 48 subjects at delta, theta, alpha, beta and gamma frequency bands by using 5 different horn sounds which are selected from the real traffic environments. Especially trucks with a high-end horn sound, show very significant differences in the brainwaves of the pedestrians. Therefore, it is very important for pedestrians to make legal arrangements related to the voice of the high horn, especially in the developed countries.

Quality index of dual shell horns of passenger cars based on a spectrum decay slope

This paper presents an objective evaluation method for the perceived quality of a car horn sound based on a psychoacoustic metric and subjective test. A new psychoacoustic metric called the “spectrum decay” (SD) is developed to evaluate a luxury timbre in the sound quality of the horn. The SD slope is found from spectrum analysis of the interior sounds produced by car horns. The interior sounds are measured and recorded from ten sampled passenger cars. The measured horn sounds are also evaluated subjectively by 41 subjects to extract the “luxury” factor. To validate the SD slope, eight synthetic sounds with a variety of SD slopes are designed. The synthetic sounds are also subjectively evaluated by the same 41 subjects. Two sound quality indexes for car horn sound are developed based on the correlation between the SD slope and subjective ratings of the synthetic sounds. One index uses a linear relationship between the SD slope and subjective rating but has a limit to its utility (i.e., the SD slope should be less than 10). The sound quality indexes are applied to the estimation of sound quality of horn sounds of ten passenger cars measured inside the cars. Correlations between the estimated subjective rating and subjective ratings evaluated by the subjects are sufficient (linear index: R = 0.84 p < 0.004, nonlinear index: R = 0.91, p < 0.001) for validation of the sound quality index.

“The Postilion’s Horn Sounds”: A Complementarity Approach to the Phenomenology of Sound-Consciousness?

In the phenomenology of the consciousness of internal time, Edmund Husserl has frequent recourse to sound and melody as illustrations of the processes that give rise to immanent temporal objects. In Husserl’s analysis, there is a philosophically pregnant tension between the geometrical diagrams representing multiple dimensions of immanent time and his intuition that time-points might be no more than fictions leading to absurdities. In this paper, I will address this tension in order to motivate a complementarity approach to temporal objects such as sound and melody that might illuminate the phenomenology of sound-consciousness.

The Reliability Analysis of Car Electronic Horn Sound Level Based on the Fault Tree

Through access to information obtained by the probability of the basic event to occur as the known data, using the structure function method of the diagram analysis and fault tree calculation method, calculated the probability about the sound level decline of car electronic horn, then known reliability and tested the sound level aspects of the car electronic horn is the stable and reliable, found out the main reasons of the sound level decline at the same time, proposed the prevention and improvement measures, improved the reliability of the car electric horn in sound level by the implementing measures.

A noise mapping study for heterogeneous road traffic conditions considering horn sounds.

In recent years noise mapping has become an increasingly useful tool for environmental noise assessment. Noise mapping is the process of determining and visualizing noise impact on the environment. The current noise mapping softwares are typically designed for the express and freeways of other countries where the roads are widely open with the homogeneous traffic conditions and speeds of vehicles touching 100 km/h. This situation is not suitable for Indian conditions where heterogeneity of traffic and honking of vehicles are the characteristics in an urban environment. A pilot study in typical areas of a metropolitan city (Chennai city) using soundplan software shows a difference of up to 7 to 10 dB(A) in Lden values between obtained and measured noise levels. A multiple regression model has been developed taking into account the horn aspects and heterogeneity. The statistical parameters such as L10, L50, L90, and Leq are measured along with the vehicle speed. The vehicle count and number of horn events are also observed during the field measurements with the video camera. The developed multiple regression models can be used as a plug‐in in any open source GIS softwares such as QGIS, GRASS, etc., for noise mapping purposes. With this background this paper explains a methodology to build 3‐D noise models for urban areas to analyze and visualize the 3‐D distribution.