Minimum classification error training for speaker identification using Gaussian mixture models based on multi-space probability distribution

Citations Over Time

Abstract

In our previous work, we have proposed a speaker modeling technique using spectral and pitch features for text-independent speaker identification based on Multi-Space Probability Distribution Gaussian Mixture Models (MSD-GMMs). We have presented a maximum likelihood (ML) estimation procedure for the MSD-GMM parameters and demonstrated its high recognition performance. In this paper, we describe an minimum classification error (MCE) training procedure for the MSDGMM speaker models. MCE training is also applied to automatically estimate mixture-dependent stream weights for spectral and pitch streams. The MCE-based MSD-GMM speaker models are evaluated for a text-independent speaker identification task. Experimental results show that MCE training of the MSD-GMM parameters significantly reduces identification errors and system performance is further improved by appropriately weighting spectral and pitch streams using MCE training.

Related Papers

• → An investigation on speaker vector-based speaker identification under noisy conditions(2008)5 cited
• Gaussian Mixture Model: A Modeling Technique for Speaker Recognition and its Component(2015)
• → GMM and ANN Hybrid Model and its Application in Speaker Identification(2009)1 cited
• A Real Time Speaker Recognition System Based on GMM(2007)
• → Method and apparatus for speaker identification using mixture discriminant analysis to develop speaker models(2002)