Objective evaluation of the rumbling sound in passenger cars based on an artificial neural network

Abstract A rumbling sound is one of the most important sound qualities in a passenger car. In previous work, a method for objectively evaluating the rumbling sound was developed based on the principal rumble component. In the present paper, the rumbling sound was found to relate effectively not only to the principal rumble component but also to the loudness and roughness. The last two subjective parameters are sound metrics in psychoacoustics. The principal rumble component, roughness, and loudness were used as the sound metrics for the development of the rumbling index to evaluate the rumbling sound objectively. The relationship between the rumbling index and these sound metrics is identified by an artificial neural network. Interior sounds of 14 passenger cars were measured, and 21 passengers subjectively evaluated the rumbling sound qualities of these interior sounds. Through this research, it was found that the results of these evaluations and the output of a neural network have a high correlation. The rumbling index has been successfully applied to the objective evaluation of the rumbling sound quality of mass-produced passenger cars.