Text-Independent Speaker Identification Using Gaussian Mixture Models Based on Multi-Space Probability Distribution

摘要

This paper presents a new approach to model- ing speech spectra and pitch for text-independent speaker iden- tification using Gaussian mixture models based on multi-space probability distribution (MSD-GMM). MSD-GMM allows us to model continuous pitch values of voiced frames and discrete symbols for unvoiced frames in a unified framework. Spectral and pitch features are jointly modeled by a two-stream MSD- GMM.