Comparative study of several novel acoustic features for speaker recognition

Finding good features that represent speaker identity is an important problem in speaker recognition area. Recently a number of novel acoustic features have been proposed for speaker recognition. The researchers use different data sets and sometimes different classifiers to evaluate the features and compare them to the baselines such as MFCC or LPCC. However, due to different experimental conditions direct comparison of those features to each other is difficult or impossible. This paper presents a study of five new recently proposed acoustic features using the same data (NIST 2001 SRE), and the same UBM-GMM classifier. The results are presented as DET curves with equal error ratios indicated. Also, an SVM-based combination of GMM scores produced on different features has been made to determine if the new features carry any complimentary information. The results for different features as well as for their combinations are directly comparable to each other and to those obtained with the baseline MFCC features.