Speaker identification using hybrid Karhunen–Loeve transform and Gaussian mixture model approach

摘要

This paper proposes a classification scheme that incorporates Karhunen–Loeve transform (KLT) and Gaussian mixture model (GMM) for text-independent speaker identification. Our results show that the combination is beneficial to both classification accuracy and computational cost. For a database with 500 Mandarin speakers, it is demonstrated that accuracy improvement of up to 4% and computational cost saving of 10 times compared to those of the conventional GMM model can be achieved.