@InProceedings{Sering2023_1181,
author = {Konstantin Sering and Paul Schmidt-Barbo},
booktitle = {Studientexte zur Sprachkommunikation: Elektronische Sprachsignalverarbeitung 2023},
title = {Somatosensory Feedback in PAULE},
year = {2023},
editor = {Christoph Draxler},
month = mar,
pages = {119--126},
publisher = {TUDpress, Dresden},
abstract = {A somatosensory pathway is added to the Predictive Articulatory speech
synthesis Utilizing Lexical Embeddings (PAULE) model. The different choices
that lead to the specific somatosensory representation and the pathway are discussed.
PAULE is a continuously improved control model for the articulatory
speech synthesizer VocalTractLab (VTL) that directly facilitates a meaning representation
to find suitable motor trajectories and does not use any symbolic units
neither for the motor representation nor for the acoustic or semantic representation.
The somatosensory representation consists of the minimal cross-sectional area in
each of the most frontal 1-centimeter intervals of the oral cavity of the VTL plus the
incisor position, the tongue tip elevation, and the velum opening. In the somatosensory
pathway the 10-dimensional somatosensory representation is used as an intermediate
representation before predictions in the acoustic and semantic goal space
are compared against targets. The semantic and acoustic sources of error along the
somatosensory and along the acoustic pathway are added together with an effort
minimization term on the control parameter (cp-)trajectories of the VTL to form an
additive loss. This additive loss is minimized to plan optimal cp-trajectories that
result in a copy-synthesis of a target acoustics with the VTL.},
isbn = {978-3-95908-303-4},
issn = {0940-6832},
keywords = {Speech Pathology},
url = {https://www.essv.de/pdf/2023_119_126.pdf},
}