We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Analysis and Assessment of Controllability of an Expressive Deep Learning-Based TTS System.
- Authors
Tits, Noé; El Haddad, Kevin; Dutoit, Thierry
- Abstract
In this paper, we study the controllability of an Expressive TTS system trained on a dataset for a continuous control. The dataset is the Blizzard 2013 dataset based on audiobooks read by a female speaker containing a great variability in styles and expressiveness. Controllability is evaluated with both an objective and a subjective experiment. The objective assessment is based on a measure of correlation between acoustic features and the dimensions of the latent space representing expressiveness. The subjective assessment is based on a perceptual experiment in which users are shown an interface for Controllable Expressive TTS and asked to retrieve a synthetic utterance whose expressiveness subjectively corresponds to that a reference utterance.
- Subjects
CONTROLLABILITY in systems engineering; AFFECTIVE computing; SPEECH synthesis; ARTIFICIAL intelligence; BLIZZARDS; AUDIOBOOKS
- Publication
Informatics, 2021, Vol 8, Issue 4, p84
- ISSN
2227-9709
- Publication type
Article
- DOI
10.3390/informatics8040084