|
Edinburgh Research Archive >
Centre for Speech Technology Research >
CSTR publications >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/1842/1049
|
| Title: | Confidence Measures for Evaluating Pronunciation Models |
| Authors: | Williams, Gethin
Renals, Steve |
| Issue Date: | May-1998 |
| Citation: | Modeling Pronunciation Variation for Automatic Speech Recognition, Rolduc, The Netherlands, May 4-6, 1998, ed. by Helmer Strik, Judith M. Kessens, and Mirjam Wester. pp. 151-156. |
| Publisher: | International Speech Communication Association |
| Abstract: | In this paper, we investigate the use of confidence measures for the evaluation of pronunciation models and the employment of these evaluations in an automatic baseform learning process. The confidence measures and pronunciation models are obtained from the ABBOT hybrid Hidden Markov Model/Artificial Neural Network (HMM/ANN) Large Vocabulary Continuous Speech Recognition (LVCSR) system [8]. Experiments were carried out for a number of baseform learning schemes using the ARPA North American Business News (NAB) and the Broadcast News (BN) corpora from which it was found that a confidence measure based scheme provided the largest reduction in Word Error Rate (WER). |
| URI: | http://www.isca-speech.org/archive/mpv_98
http://hdl.handle.net/1842/1049 |
| Appears in Collections: | CSTR publications
|
Items in ERA are protected by copyright, with all rights reserved, unless otherwise indicated.
|
