Synthesizing speech with selected perceptual voice qualities - A case study with creaky voice

TL;DR

This paper demonstrates a TTS system capable of manipulating creaky voice qualities using a flow-based control mechanism, enabling perceptual voice quality control without relying on frame-wise predictors.

Contribution

It introduces a novel TTS approach with a global voice quality manipulation block based on normalizing flows, improving control over creaky voice qualities.

Findings

Successful manipulation of creaky voice confirmed by listening tests

Achieved perceptual control with only slight reduction in MOS score

Avoided unreliable frame-wise creak prediction

Abstract

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.