Improving the Slovak LVCSR performance by cluster-sensitive acoustic model retraining

Abstract

In this paper, we present a cluster-dependent adaptation approach for HMM-based acoustic models. The proposed approach employs clustering techniques to group the original training utterances into clusters with predefined number. The clustered speech data are intended to adapt an initially pre-trained acoustic model to the specific cluster by reestimation based on the standard Baum-Welch procedure. The resulting model, adapted to the homogeneous data may markedly improve the baseline recognition rate, whereas the model complexity may be reduced. In the recognition step, the test samples are scored by each adapted model and the most accurate one is chosen. The proposed approach is thoroughly evaluated in Slovak triphone-based large vocabulary continuous speech recognition (LVCSR) system. The results prove that the cluster-sensitive retraining leads to significant improvements over the baseline reference system trained according to the conventional training procedure.