Pronunciation Modelling In The Rwth Large Vocabulary Speech Recognizer (1998)
| Citations: | 8 - 0 self |
BibTeX
@MISC{Beulen98pronunciationmodelling,
author = {K. Beulen and J. Overmann and A. Eiden and S. Martin and L. Welling and J. Overmann and H. Ney},
title = {Pronunciation Modelling In The Rwth Large Vocabulary Speech Recognizer},
year = {1998}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
this paper we describe the application of pronunciation variants for our large vocabulary continuous speech recognizer. We will explain how the pronunciation variants were used in training and recognition and give some recognition results on three different corpora. The recognition tests were performed on the Wall Street Journal (WSJ) November 92 development and evaluation corpora (5 000 words), the North American Business (NAB) H1 development corpus (20 000 words) and on the Verbmobil 1996 evaluation corpus (5 000 words). For the WSJ and NAB corpora, a slight improvement in recognition accuracy can be observed, while for the Verbmobil corpus the error rate remains unchanged
