|
Authors: | René Beutler, Beat Pfister |
Group: | Computer Engineering |
Type: | Misc |
Title: | Integrating statistical and rule-based knowledge for continuous German speech recognition |
Year: | 2003 |
Month: | October |
Pub-Key: | BP03b |
Abstract: | A new approach to continuous speech recognition (CSR) for German is presented, which integrates both statistical knowledge (at the acoustic-phonetic level) and rule-based knowledge (at the word and sentence levels). We introduce a flexible framework allowing bidirectional processing and virtually any search strategy given an acoustic model and a context-free grammar. An implementation of this class of recognizers by means of a word spotter and an island char parser is presented. A word accuracy of 93.5 is reported on a speaker dependent recognition task with a 4k words dictionary. |
Howpublished: | Poster Presentation for (IM)2 NCCR Review Panel, Hotel du Parc, Martigny, Switzerland |
Resources: | [BibTeX] |