Intersession Variability Compensation in Language and Speaker Identification

Varibiality in the channel and session is an important issue in the text-independent speaker recognition task. To date, several techniques providing channel and session variability compensation were introduced in a number of scientic papers. Such implementation can be done in feature, model and score domain. Relatively new and powerful approach to remove channel distortion is so-called eigenchannel adaptation for Gaussian Mixture Models (GMM). The drawback of the technique is that it is not applicable in its original implementation to different types of classifiers, eg. Support Vector Machines (SVM), GMM with different number of Gaussians or in speech recognition task using Hidden Markov Models (HMM). The solution can be the approximation of the technique, eigenchannel adaptation in feature domain. Both, the original eigenchannel adaptation and eigenchannel adaptation on features in task of speaker recognition are presented. After achieving good results in speaker recognition, contribution of the same techniques was examined in acoustic language identification system with $14$ languages. In this task undesired factors are channel and speaker variability. Presented results are presented on the NIST Speaker Recognition Evaluation 2006 data and NIST Language Recognition Evaluation 2007 data.

Speaker identification, language identification, accoustic system, session variability, inter-speaker variability, channel compensation, eigenchannel adaptation, eigenfeatures