Akagi Masato
Modeling of contextual effect
based on spectral peak interaction
Abstract:This paper presents a model of a lower level contextual effect that can cope
with co-articulation problems, especially vowel neutralization. The model is constructed
to overshoot spectral peak trajectories based on spectral peak interaction, assuming
that the lower level contextual effect is represented as the sum of the interaction
function between each spectral peak pair. The interaction function is determined experimentally
in order to reduce the distance between a real spectral peak and its target
which is a spectral peak mean computed for vowels uttered in isolation. The interaction
function thus determined suggests that spectral peak interaction plays some
important roles in the contextual effect and recovers phoneme characteristics from
neutralization. Applying the determined interaction function to real speech data to
cope with vowel neutralization, spectral peak trajectory overshoot, spectral peaks at
the vowel center approach their own targets, and the distance between each vowel
category pair increases.