Sixth International Conference on Spoken Language Processing
(ICSLP 2000)

Beijing, China
October 16-20, 2000

Improved MLLR Speaker Adaptation Using Confidence Measures for Conversational Speech Recognition

Michael Pitz, Frank Wessel, Hermann Ney

Lehrstuhl für Informatik VI, Computer Science Department, RWTH Aachen - University of Technology, Aachen, Germany

Automatic recognition of conversational speech tends to have higher word error rates (WER) than read speech. Improvements gained from unsupervised speaker adaptation methods like Maximum Likelihood Linear Regression (MLLR) [1] are reduced because of their sensitivity to recognition errors in the first pass. We show that a more detailed modeling of adaptation classes and the use of con- fidence measures improve the adaptation performance. We present experimental results on the VERBMOBIL task, a German conversational speech corpus.

Reference

  1. C.J. Leggetter, P.C.Woodland: "Maximum Likelihood linear regression for speaker adaptation of continuous density hidden Markov models", Computer, Speech and Language, vol. 9, pp. 171-185, 1995.


Full Paper

Bibliographic reference.  Pitz, Michael / Wessel, Frank / Ney, Hermann (2000): "Improved MLLR speaker adaptation using confidence measures for conversational speech recognition", In ICSLP-2000, vol.4, 548-551.