• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2007.05a
• /
• pp.137-140
• /
• 2007

A prediction model for the sound quality of household refrigerator noise was proposed by investigating subjective and objective attributes of the noise [Jeon et al. (2007) Appl. Acoust.]. In the present study, the just noticeable difference (JND) of each sound quality metric - Zwicker's loudness, sharpness, roughness and fluctuation strength - which constitute the prediction model was investigated. Loudness of recorded sound samples from five refrigerators were varied according to constant intervals in sound pressure levels. Sharpness was also changed at 14-16 barks. Auditory experiments were conducted to discriminate the JNDs of loudness and sharpness by method of limit. The results indicated that JNDs of loudness and sharpness were 0.50 sone and 0.08 acum, respectively.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2004.05a
• /
• pp.991-996
• /
• 2004

The international competition in refrigerator markets has continuously required the research for sound quality of a refrigerator to improve the quality of a life. In this paper, A new method for evaluation of the sound quality of a refrigerator is developed based on human sensibility engineering by using ANN(Artificial neural network). Finally it is applied to evaluate the sound qualify of refrigerator on the production line.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2006.11a
• /
• pp.654-660
• /
• 2006

There are various sounds in the car as much as cats have many mechanical parts. These sounds make various sound qualities. The international competition in car markets has continuously required the research about the sound quality of a car. The domestic carmakers have also invested a lot of money for the research and development of sound quality. Car axle plays an important role in a vehicle and its NVH development is also important. By this time, NVH development of car axle is mainly based on the reduction of sound pressure level(dBA), which cannot gives, the satisfaction to the customers in view of the sound quality of a vehicle. Therefore, in this project, a sound quality index evaluating the sound quality of axle noise based on human sensibility is developed and applied to the development of the sound quality of axle noise

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.25 no.3
• /
• pp.141-149
• /
• 2015

In this study, there is an investigation about the sound quality of automotive horn that attached to luxury sedans. In order to define a questionnaire of horn sound quality the factor analysis is conducted. Ten automotive horns are selected for this research and ten passenger cars(nine is luxury sedan and one economy class car). Luxury is used for the questionnaire as an attribute for the sound quality of car horn. The interior noises for ten test cars are recorded and used for the subjective analysis of car horn sound. In the paper, new sound metric for the car horn sound is presented. The new sound metric is used for the objective sound index for the prediction of subjective sound quality of car horn.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.16 no.9 s.114
• /
• pp.897-903
• /
• 2006

The reduction of the vehicle interior noise has been the main interest of noise and vibration harshness (NVH) engineers. The driver's perception on the vehicle noise is affected largely by psychoacoustic characteristic of the noise as well as the SPL. In particular, the heating, ventilation and air conditioning (HVAC) system sound among the vehicle interior noise has been reflected sensitively in psychoacoustics view point. Even though the HVAC noise is not louder than overall noise level, it clearly affects subjective perception to drivers in the way of making to be nervous or annoyed. Therefore, these days a vehicle engineer takes aim at developing sound quality as well as reduction of noise. In this paper, we acquired noises in the HVAC from many vehicles. Through the objective and subjective sound quality (SQ) evaluation with acquiring noises recorded by the vehicle HVAC system, the simple and multiple regression models were obtained for the subjective evaluation 'Pleasant' using the semantic differential method (SDM). The regression procedure also allows you to produce diagnostic statistics to evaluate the regression estimates including appropriation and accuracy. Furthermore, the neural network (NN) model were obtained using three inputs(loudness, sharpness and roughness) of the SQ metrics and one output(subjective 'Pleasant'). Because human's perception is very complex and hard to estimate their pattern, we used NN model. The estimated models were compared with correlations between output indexes of SQ and hearing test results for verification data 'Pleasant'. As a result of application of the SQ indexes, the NN model was shown with the largest correlation of SQ indexes and we found possibilities to predict the SQ metrics.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2006.05a
• /
• pp.1272-1275
• /
• 2006

The A-weighting curve, very well explain the human perception for various frequency, is used to assess the traffic noise as well as the environmental noise. However, it does not reflect the annoyance perception appropriately because it assesses the noise at an A-weighted equivalent noise level of 1 kHz. In this study, we acquired the sound quality of traffic noise included various frequency and studied the human perception caused by change of frequency range.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.605-607
• /
• 2023

Recent research has highlighted the effectiveness of Deep Learning (DL) techniques in automating the detection of lung sound anomalies. However, the available lung sound datasets often suffer from limitations in both size and balance, prompting DL methods to employ data preprocessing such as augmentation and transfer learning techniques. These strategies, while valuable, contribute to the increased complexity of DL models and necessitate substantial training memory. In this study, we proposed a streamlined and lightweight DL method but effectively detects lung sound anomalies from small and imbalanced dataset. The utilization of 1D dilated convolutional neural networks enhances sensitivity to lung sound anomalies by efficiently capturing deep temporal features and small variations. We conducted a comprehensive evaluation of the ICBHI dataset and achieved a notable improvement over state-of-the-art results, increasing the average score of sensitivity and specificity metrics by 2.7%.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2006.11a
• /
• pp.636-640
• /
• 2006

In this study, metrics for evaluation of heavy-weight impact noise were investigated. Heavy-weight impact noises generated by impact ball were recorded in real apartments using binaural microphone. Those sounds were classified into three groups according to frequency characteristics in order to control aspects which affect subjective responses to heavy-weight impact noise. Sound sources for auditory experiment were selected based on the classification result. Then auditory experiments were conducted to investigate the relationship between level indices and subjective responses. The results showed that $L_{Aeq},\;L_{Amax}$ and $LL_z$ as well as $L_{iFmax,AW}$ were highly correlated with subjective response. Therefore, $L_{Aeq}$ and $L_{Amax}$ can be used as metrics for evaluation of heavy-weight impact noise. In further studies, it is needed to verify classification of heavy-weight impact noise generated by bang machine and impact ball.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2002.05a
• /
• pp.1157-1160
• /
• 2002

This paper describes an investigative study for Wind Noise of Passenger Cars. Using statistical method of analyzing jury preference data, we extract important sound quality metrics for subjective feeling and also md important frequency band. It will be helpful for development of wind Noise improvement.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2007.11a
• /
• pp.318-321
• /
• 2007

Since human listening is very sensitive to sound, a subjective index of a sound quality is required. Therefore, in the analysis for each situation, the sound evaluation is composed with sound quality factor. Many researchers spends their effort to make a more reliable and more accurate of sound in term of sound quality index for various system noise. The previous methods to evaluation of the SQ about vehicle interior noise are linear regression analysis of subjective SQ metrics by statistics and the estimation of the subjective SQ values by neural network. But these are so depended on jury test very much that they result in many difficulties. So, to reduce jury test weight, we suggested a new method using Mahalanobis distance for SQ evaluation. Threrefore, in this study Mahalanobis distance for the vehicle interior noise was derived using the objective SQ except jury test. Finnaly, the results of the SQ evaluation was analyzed discrimination between reference and abnormal group.