|COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring.|
Modelling trajectories in statistical speech synthesis
If you have a question about this talk, please contact Kai Yu.
This is the second talk of the speech synthesis seminar series.
In statistical speech synthesis we build a probabilistic model of (processed) speech given (processed) text. The processed speech is in the form of a sequence of acoustic feature vectors, and the sequence over time of each component of this feature vector forms a trajectory. In this talk we’ll discuss how to model these trajectories.
We will first review a few ways in which the standard HMM synthesis model is unsatisfactory. In particular the standard model is unnormalized, and we’ll discuss the practical impact of this lack of normalization. We’ll then look at normalized approaches, including the trajectory HMM (a globally normalized model) and the autoregressive HMM (a locally normalized model). Finally we’ll discuss some other possible enhancements including minimum generation error (MGE) training.
This talk is part of the speech synthesis seminar series series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
Other listsPsychology Language and Music as Cognitive Systems Production Processes Group
Other talksUnderstanding & Exploiting the NKT cell:CD1d System in Cancer and Other Diseases Inferno XXV, Purgatorio XXV, Paradiso XXV Understanding Mechanisms of Sterile Inflammation Scribes, 'scribes' and language contact in Greco-Roman Egypt The ice-covered ocean: too big a challenge for climate models? Developmental Programming Seminars: Healthy Hearts Picked from the Family Tree