Show simple item record

The effect of using normalized models in statistical speech synthesis

dc.creatorShannon, Matt
dc.creatorZen, Heiga
dc.creatorByrne, William Joseph
dc.description.abstractThe standard approach to HMM-based speech synthesis is inconsistent in the enforcement of the deterministic constraints between static and dynamic features. The trajectory HMM and autoregressive HMM have been proposed as normalized models which rectify this inconsistency. This paper investigates the practical effects of using these normalized models, and examines the strengths and weaknesses of the different models as probabilistic models of speech. The most striking difference observed is that the standard approach greatly underestimates predictive variance. We argue that the normalized models have better predictive distributions than the standard approach, but that all the models we consider are still far from satisfactory probabilistic models of speech. We also present evidence that better intra-frame correlation modelling goes some way towards improving existing normalized models.
dc.publisherISCA (International Speech Communication Association)
dc.rightsAttribution 2.0 UK: England & Wales
dc.subjectHMM-based speech synthesis
dc.subjectacoustic modelling
dc.subjectautoregressive HMM
dc.subjecttrajectory HMM
dc.titleThe effect of using normalized models in statistical speech synthesis
dc.typeConference Object

Files in this item


This item appears in the following Collection(s)

Show simple item record