ESCA Workshop on Prosody Lund, Sweden September 27-29, 1993

Improving the Prosody in TTS Systems: Morphological and Lexical-Semantic Methods for Tracking 'New' vs. 'Given' Information

Merle Horne (1), Marcus Filipsson (1), Christer Johansson (1), Mats Ljungqvist (2), Anders Lindstrom (2)

(1) Dept. of Linguistics and Phonetics, University of Lund, Lund, Sweden
(2) INFOVOX, Solna, Sweden

The design of an algorithm for referent tracking in a restricted domain is presented. The algorithm allows one to preprocess a text and automatically tag words as either contextually 'New' or 'Given'. The procedure involves computational modelling of lexical semantic identity of sense relations as well as information on inflexional/derivational morphology and compounding. Referent identity is defined on head-word representations derived from the text input on the basis of the inflexional expansion rules contained in a lemmatized lexicon of Swedish. Information on the New/Given status of words can subsequently be used in the F0-generating component of the text-to-speech system, to trigger the assignment of focal vs non-focal word accents.

Full Paper

Bibliographic reference.  Horne, Merle / Filipsson, Marcus / Johansson, Christer / Ljungqvist, Mats / Lindstrom, Anders (1993): "Improving the prosody in TTS systems: morphological and lexical-semantic methods for tracking 'new' vs. 'given' information", In Prosody-1993, 208-211.