Fourth ISCA ITRW on Speech Synthesis
August 29 - September 1, 2001
The width and the position of the pitch range reveals important
information about the structure of a spoken discourse. This
paper studies the correlation between the pitch range and the
discourse structure based on a large database. The model used
to analyze the discourse is based on a two-level description of
registers. Frimary register features reflect the prosodic phrasing
within a discourse segment. The secondary register features
depend on the relations between the discourse segments, more
specifically the topic structure of the discourse. The pitch-range
is automatically extracted from a speech database with the help
of an F0 parametrization. This study shows that different registers
exhibit pitch range values that differ clearly in position
and width. These results can be used to successfully implement
a global prominence model within a speech synthesis system.
The ideal application is concept-to-speech, where discourse in-
formation is in principle available on the input side.
Bibliographic reference. Möhler, Gregor / Mayer, Jörg (2001): "A Discourse Model for Pitch-Range Control", In SSW4-2001, paper 114.