Sound Quality Prediction of Vehicle Interior Noise During Acceleration Using Least Square Support Vector Machine

Based on Least Square Support Vector Machine (LSSVM) algorithm, a Sound Quality Prediction (SQP) model of vehicle interior noise during acceleration is presented in this study. The objective psychoacoustic parameters and subjective annoyance results are used as the input and output of the model, respectively. With correlation analysis, some psychoacoustic parameters, such as loudness, sharpness, roughness, articulation index and tonality, are selected for the modeling. The estimated values of unknown samples with the LSSVM SQP model are highly correlated with the subjective annoyance values, which has a higher accuracy than that with Multiple Linear Regression (MLR) model. Results show that the proposed LSSVM SQP model has good generalization ability and can be applied to the sound quality prediction of vehicle interior noise during acceleration.