The application of discriminative training techniques in LID system fusion

This paper reports an approach to language identification (LID) system fusion using discriminative training. Maximum mutual information (MMI) training for Gaussian mixture model is introduced to the standard LDA-GMM fusion framework. Experimental results show that the proposed fusion scheme outperforms the maximum likelihood (ML) trained backend of LID system. The impact of number of Gaussian mixtures on fusion performance is also discussed.