PROSODIC DISAMBIGUATION FROM DEEP SYNTACTIC STRUCTURES

Philipp von Böselager1 & Berthold Crysmann2
1IfL Phonetik, University of Cologne; 2DFKI & Saarland University

ID 1429
[full paper]

In this paper, we report on an experiment showing how the introduction of detailed prosodic information into synthetic speech leads to better disambiguation of structurally ambiguous sentences. Using modifier attachment (MA) ambiguities and subject/object fronting (OF) in German as test cases, we show that prosody which is automatically generated from deep syntactic information can lead to considerable disambiguation effects, and can even override a strong semantics-driven bias. The architecture used in the experiment, consisting of a large-scale generator for German, a prosody module, and the speech synthesis system MARY is shown to be a valuable platform for testing hypotheses in intonation studies.