minimum classification error linear regression for acoustic model adaptation of continuous density HMMS

Authors:
Xiaodong He;Wu Chou
Affiliations:
Dept. of Comput. Eng. & Comput. Sci., Missouri Univ., USA;Dept. of Comput. Sci. & Eng., Indian Inst. of Technol., Madras, India
Venue:
ICME '03 Proceedings of the 2003 International Conference on Multimedia and Expo - Volume 2
Year:
2003

Citing 0
Cited 3

Large-margin minimum classification error training: A theoretical risk minimization perspective

Computer Speech and Language
Recognition of noisy speech: a comparative survey of robust model architecture and feature enhancement

EURASIP Journal on Audio, Speech, and Music Processing
Personalized ranking model adaptation for web search

Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a concatenated "super" string model based minimum classification error (MCE) model adaptation approach is described. We show that the error rate minimization in the proposed approach can be formulated into maximizing a special ratio of two positive functions. The proposed string model is used to derive the growth transform based error rate minimization for MCE linear regression (MCELR). It provides an effective solution to apply MCE approach to acoustic model adaptation with sparse data. The proposed MCELR approach is studied and compared with the maximum likelihood linear regression (MLLR) based model adaptation. Experiments on large vocabulary speech recognition tasks are performed. Experimental results indicate that the proposed MCELR model adaptation can lead to significant speech recognition performance improvement and its performance advantage over the MLLR based approach is observed even when the amount of adaptation data is sparse.