APPLICATION OF FUJISAKI MODEL TO DERIVE FEATURES TO CAPTURE PROSODIC INFORMATION.
Main Article Content
Abstract
The usefulness of a model for characterising pitch profiles in voice signals is critical in a
wide range of application areas, but it is particularly important in natural-sounding text-tospeech
systems, which are becoming increasingly popular. Despite its simplicity, the Fujisaki
model has demonstrated remarkable accuracy across a wide range of languages. A much
more difficult task is that of solving the inverse problem, i.e., extracting the input parameters
that formed an observed pitch contour, which has the potential to be very beneficial in the
field of automatic extraction of prosodic parameters from a given speech signal and could be
of considerable importance A tiny sample of 100 male and female utterances from the
natural, USS, and HTS systems were used to establish the Fujisaki Model parameters
speakers was used. Both natural and synthetic speech are produced using the same text
content.
Downloads
Metrics
Article Details
Licensing
TURCOMAT publishes articles under the Creative Commons Attribution 4.0 International License (CC BY 4.0). This licensing allows for any use of the work, provided the original author(s) and source are credited, thereby facilitating the free exchange and use of research for the advancement of knowledge.
Detailed Licensing Terms
Attribution (BY): Users must give appropriate credit, provide a link to the license, and indicate if changes were made. Users may do so in any reasonable manner, but not in any way that suggests the licensor endorses them or their use.
No Additional Restrictions: Users may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.