Objective Evaluation of Exciting Engine Sound in Passenger Compartment During Acceleration

The Influence of the Directivity of the Speaker in the Car on the Subjective Sound Quality Evaluation

“…The artificial neural network algorithm is suitable for model establishment of large-sample nonlinear complex problems, and the prediction accuracy is good. Lee and Kim et al [24][25][26] summarized the work of Hatano [27], Terazawa [28], pointing out that roar and rumble are the main characteristics of acceleration sound, and the roar has a strong correlation with the loudness and sharpness in the 200Hz band of the sound sample, while the loudness and roughness in the 200Hz~500Hz band have a significant impact on the rumble, and the ANN algorithm is used to establish a prediction model of roar and rumble index. Shin et al [29] proposed a quantitative measure of roar intensity to measure roar level.…”