The control of perceptual voice qualities in a text-to-speech (TTS) system is of interest for applications where unmanipu- lated and manipulated speech probes can serve to illustrate pho- netic concepts that are otherwise difficult to grasp. Here, we show that a TTS system, that is augmented with a global speaker attribute manipulation block based on normalizing flows1 , is capable of correctly manipulating the non-persistent, localized quality of creaky voice, thus avoiding the necessity of a, typi- cally unreliable, frame-wise creak predictor. Subjective listen- ing tests confirm successful creak manipulation at a slightly re- duced MOS score compared to the original recording.
@article{arxiv.2511.05143,
title = {Synthesizing speech with selected perceptual voice qualities - A case study with creaky voice},
author = {Frederik Rautenberg and Fritz Seebauer and Jana Wiechmann and Michael Kuhlmann and Petra Wagner and Reinhold Haeb-Umbach},
journal= {arXiv preprint arXiv:2511.05143},
year = {2025}
}