Sixth International Conference on Spoken Language Processing
(ICSLP 2000)

Beijing, China
October 16-20, 2000

A Novel Loss Function for the Overall Risk Criterion Based Discriminative Training of HMM Models

Janez Kaiser, Bogomir Horvat, Zdravko Kacic

University of Maribor, Faculty of Electrical Engineering and Computer Science, Maribor, Slovenia

In this paper, we propose a novel loss function for the overall risk criterion estimation of hidden Markov models. For continuous speech recognition, the overall risk criterion estimation with the proposed loss function aims to directly maximise word recognition accuracy on the training database. We propose reestimation equations for the HMM parameters, which are derived using the Extended Baum-Welch algorithm. Using HMM, trained with the proposed method, a decrease of word recognition error rate of up to 17.3% has been achieved for the phoneme recognition task on the TIMIT database.

Full Paper

Bibliographic reference.  Kaiser, Janez / Horvat, Bogomir / Kacic, Zdravko (2000): "A novel loss function for the overall risk criterion based discriminative training of HMM models", In ICSLP-2000, vol.2, 887-890.