|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 listsSir Richard Stone Annual Lecture FERSA (Faculty of Education Research Students' Seminars) 2010-2011 The International Year of Statistics 2013 - Series of Public Lectures
Other talksCambridge Public Policy Lecture: Rt Hon Vince Cable, MP Darmon points for number fields of mixed signature CGHR Research Group: “Suspending Rights: The State of Emergency in armed conflicts between legal exception and case-law practice" Joint determinants of prefrontal ageing: Selective frontal grey and white matter differentially mediate age-related changes in fluid intelligence and multitasking The unknowable, the new reformation, and the rationale for religious freedom: the place of religion in Spencer's philosophy Drug discovery