Abstract
Phrasing and intonation modelling are usually carried out as separate processes. This is not an optimal approach, especially in the case of intonation unit-selection systems. Proposed is a novel approach that integrates both phrasing and intonation modules in a single stage, considering several prosodic structures and obtaining the best combination of prosodic structure and intonation units for each input sentence.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have