This paper presents a comparison and evaluation between the conventional maximum likelihood estimation based adaptation and different discriminative adaptation criteria. The performance of different LR and MAP adaptation are compared respectively, and the strategies of first applying LR then MAP based on both MLE and DT criteria are evaluated. The effect of the amount of available data for adaptation is also compared in our experiments. The experiment results of 863 and Tsinghua mandarin evaluation tasks suggests that the process of first applying MWCE-LR then MWCE-MAP can achieve the best performance. Index Terms— Adaptation, Discriminative training, Minimum word classification error, Speech recognition
Cite as: Zhu, B., Yan, Z.-J., Hu, Y., Wang, Z.-G., Dai, L.-R., Wang, R.-H. (2008) Investigation on Adaptation Using Different Discriminative Training Criteria Based Linear Regression and Map. Proc. International Symposium on Chinese Spoken Language Processing, 93-96
@inproceedings{zhu08_iscslp,
author={Bo Zhu and Zhi-Jie Yan and Yu Hu and Zhi-Guo Wang and Li-Rong Dai and Ren-Hua Wang},
title={{Investigation on Adaptation Using Different Discriminative Training Criteria Based Linear Regression and Map}},
year=2008,
booktitle={Proc. International Symposium on Chinese Spoken Language Processing},
pages={93--96}
}