@InProceedings{Eliseeva2024_1204,
author = {Uliana Eliseeva and Ivan Yuen and Bernd Möbius},
booktitle = {Studientexte zur Sprachkommunikation: Elektronische Sprachsignalverarbeitung 2024},
title = {Perception of Formant Distortion in German Words and Non-words},
year = {2024},
editor = {Timo Baumann},
month = mar,
pages = {46--53},
publisher = {TUDpress, Dresden},
abstract = {Concatenative text-to-speech (TTS) systems remain a widely used
cheaper alternative to neural TTS systems. Yet concatenation of prerecorded units
entails some drawbacks, such as spectral distortion, the perceptual consequences
of which remain unclear. In an attempt to bridge this gap, our study focused on
the effect of spectral distortion in vowel formants on perceived speech quality in
naturally-read manipulated German words as well as non-words. More specifically,
we explored the distortion effect on a varying number of affected formants, at different
magnitude and directionality in two corner vowels /a:/ and /i:/. The results
indicate that single formant manipulations have a less pronounced effect on the
listeners’ perception compared to multiple formant perturbations. The threshold at
which the distortion became generally audible was estimated to lie between 0.4 and
1.0 bandwidth. The directionality of the distortion was not found to be significant.},
isbn = {978-3-95908-325-6},
issn = {0940-6832},
keywords = {Phonetische Untersuchungen},
url = {https://www.essv.de/pdf/2024_46_53.pdf},
doi = {10.35096/othr/pub-7079},
}