Analysis and synthesis of speech prosody based on
articulatory dynamics and communicative functions: From concept to practice
University College London
The significance of prosody
research is not only the contribution to basic knowledge in speech science but
also the advancement in speech technology, particularly speech synthesis. A new
practice on intonation modeling is to test the models by regenerating the
complete acoustic features based on the model and comparing them to the
originals. This offer us truly rigorous tests of predictive power of theories
and models of speech prosody.
This tutorial will provide a
comprehensive procedure for systematically studying prosody based on a
user-friendly prosody modeling programs (ProsodyPro, PENTATrainer) that can be
used for both analysis and synthesis purposes. ProsodyPro is a Praat-based tool
that allows users to perform comprehensive prosody analysis. It is particularly
useful for large-scale systematic experimental investigation of prosody.
PENTATrainer analyzes F0 contours based on user-specified functional
annotation on the one hand and the program-internal Target Approximation model. The program uses analysis-by-synthesis
to determine the optimal parameters for user-defined prosodic categories. By
using a stochastic optimization method, the program automatically optimizes the
model parameters that can be readily used in synthesis. The same parameters,
meanwhile, can also be used as measurements for analysis purposes.
主持： 王蓓 副教授