15th International Congress of Phonetic Sciences (ICPhS-15) Barcelona, Spain August 3-9, 2003

The Keyword Lexicon - An Accent-Independent Lexicon for Automatic Speech Recognition

Christophe Van Bael (1), Simon King (2)

(1) University of Nijmegen, The Netherlands
(2) University of Edinburgh, UK

Recent work at the Centre for Speech Technology Research (CSTR) at the University of Edinburgh has developed an accent-independent lexicon for speech synthesis (the Unisyn project). The main purpose of this lexicon is to avoid the problems and cost of writing a new lexicon for every new accent needed for synthesis. Only recently (van Bael, 2002), a first attempt has been made to use the Keyword Lexicon for automatic speech recognition.

Full Paper

Bibliographic reference.  Bael, Christophe Van / King, Simon (2003): "The keyword lexicon - an accent-independent lexicon for automatic speech recognition", In ICPhS-15, 1165-1168.