@InProceedings{Hinterleitner2013_104,
author = {Florian Hinterleitner and Christoph Norrenbrock and Sebastian Möller},
booktitle = {Studientexte zur Sprachkommunikation: Elektronische Sprachsignalverarbeitung 2013.},
title = {Perceptual quality dimensions of Text-to-Speech systems in audiobook reading tasks},
year = {2013},
editor = {Petra Wagner},
month = mar,
pages = {44--49},
publisher = {TUDpress, Dresden},
abstract = {In this paper we present research on perceptual quality dimensions of text-to-speech systems in audiobook reading tasks. Therefore, we proposed a newly developed evaluation protocol for the assessment of synthetic speech in audiobook reading tasks for the Blizzard Challenge 2012. We illustrate the experimental setup of the special audiobook reading task of the Blizzard Challenge 2012 and analyze and interpret the results of the subjective listening test. Via a factor analysis, two quality dimensions could be extracted. Through the correlation between the val- ues of the rating scales and the factor values, the dimensions could be assigned to prosody & rhythm and to the listening pleasure of the user. This confirms the results of the previous study in which the current evaluation protocol was created. Also, a comparison with the perceptual quality dimensions of text-to-speech systems in different use cases led to significant similarities.},
isbn = {978-3-944331-03-4},
issn = {0940-6832},
keywords = {Sprachsynthese},
url = {https://www.essv.de/pdf/2013_44_49.pdf},
}