Non-intrusive speech quality assessment with support vector regression

We propose a new non-intrusive speech quality assessment algorithm based on Support Vector Regression (SVR) and Mel Frequency Cepstral Coefficients (MFCCs). The basic idea is to map the MFCCs into the desired quality score using SVR. The sensitivity of the MFCCs to external noise is exploited to gauge the changes in the speech signal to evaluate its perceptual quality. The use of SVR exploits the advantages of machine learning with the ability to learn complex data patterns for an effective and generalized mapping of features into a perceptual score, in contrast with the oft-utilized feature pooling process in the existing speech quality estimators. Experimental results indicate that the proposed approach outperforms the standard P.563 algorithm for non-intrusive assessment of speech quality with a total of 1792 speech files and the associated subjective scores.