Supervector Dimension Reduction for Efficient Speaker Age Estimation Based on the Acoustic Speech Signal

摘要

This paper presents a novel dimension reduction method which aims to improve the accuracy and the efficiency of speaker's age estimation systems based on speech signal. Two different age estimation approaches were studied and implemented; the first, age-group classification, and the second, precise age estimation using regression. These two approaches use the Gaussian mixture model (GMM) supervectors as features for a support vector machine (SVM) model. When a radial basis function (RBF) kernel is used, the accuracy is improved compared to using a linear kernel; however, the computation complexity is more sensitive to the feature dimension. Classic dimension reduction methods like principal component analysis (PCA) and linear discriminant analysis (LDA) tend to eliminate the relevant feature information and cannot always be applied without damaging the model's accuracy. In our study, a novel dimension reduction method was developed, the weighted-pairwise principal components analysis (WPPCA) based on the nuisance attribute projection (NAP) technique. This method projects the supervectors to a reduced space where the redundant within-class pairwise variability is eliminated. This method was applied and compared to the baseline system where no dimensionality reduction is done on the supervectors. The conducted experiments showed a dramatic speed-up in the SVM training testing time using reduced feature vectors. The system accuracy was improved by 5% for the classification system and by 10% for the regression system using the proposed dimension reduction method.