Prosody Modelling in Concept-to-Speech Generation: Methodological Issues

McKeown, Kathleen; Pan, Shimei

We explore three issues for the development of concept-to-speech (CTS) systems. We identify information available in a language-generation system that has the potential to impact prosody; investigate the role played by different corpora in CTS prosody modelling; and explore different methodologies for learning how linguistic features
impact prosody. Our major focus is on the comparison of two machine learning methodologies: generalized rule induction and memory-based learning. We describe this work in the context of multimedia abstract generation of intensive care (MAGIC) data, a system that produces multimedia brings of the status of patients who have just undergone a bypass operation.



  • thumnail for Phil._Trans._R._Soc._Lond._A-2000-McKeown-1419-31.pdf Phil._Trans._R._Soc._Lond._A-2000-McKeown-1419-31.pdf application/pdf 308 KB Download File

Also Published In

Philosophical Transactions of the Royal Society A

More About This Work

Academic Units
Computer Science
Published Here
April 8, 2013