Research on Vehicle Interior Sound Quality

With the improvement of people's living standards and the development of social economy, consumers have higher and higher requirements for comfort in addition to basic indicators such as power and economy when purchasing a car. This paper firstly collects the noise signals at the left and right ears of the driver's seat and the right ear of the passenger's seat under uniform speed conditions. Then a subjective and objective evaluation experiment was carried out. The objective evaluation is to obtain the values of psychoacoustic objective parameters such as loudness and fluctuation strength through software calculation; the subjective evaluation is to organize a jury test to subjectively score the irritability attribute of noise samples. Correlation analysis was carried out on all the scoring results of the jury, and finally the subjective evaluation score table of 36 noise samples was obtained. Finally, the correlation analysis was carried out on the subjective and objective evaluation results, and three psychoacoustic objective parameters of A-weighted sound pressure level, loudness, and fluctuation strength were selected as independent variables, and the subjective evaluation score was selected as the dependent variable. The first 32 noise samples are used to build the multiple linear regression model and the BP neural network model, the last 4 noise samples are used to test the accuracy of the model prediction, and the prediction results of the two models are compared and analyzed.